© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 12-GEMMASCOPE-RES-16K
    11. 10347
    Prev
    Next
    INDEX
    Explanations

    phrases that express certainty or describe a situation as straightforward or simple

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    the word "basically" used to introduce a simplification or restatement of something.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @jyhe0408

    discourse markers that frame a statement as an “in essence” or approximate summary (hedging/qualifying adverbs and phrases).

    oai_token-act-pair · gpt-5Triggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 12-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_12/width_16k/average_l0_130
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     atsi
    -0.35
     tajem
    -0.31
     verme
    -0.31
     mystérie
    -0.31
     mysterious
    -0.31
     misterioso
    -0.31
     organización
    -0.30
     şir
    -0.29
     legislación
    -0.29
     pourtant
    -0.29
    POSITIVE LOGITS
     basically
    1.32
    basically
    1.30
     essentially
    1.30
    Essentially
    1.27
    Basically
    1.27
    essentially
    1.27
     Basically
    1.23
     Essentially
    1.21
     practically
    1.16
     praticamente
    1.04
    Activations Density 0.321%

    No Known Activations