© 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. 28-GEMMASCOPE-RES-16K
    11. 9575
    Prev
    Next
    INDEX
    Explanations

    phrases related to decision-making and options

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

    Action after "to" or another verb

    np_acts-logits-general · gemini-2.0-flash

    decide instead

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 28-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_28/width_16k/average_l0_119
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.28.hook_resid_post
    Hook Layer
    28
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Effectively
    -0.49
     effectively
    -0.48
    OCCURRED
    -0.47
     significance
    -0.45
     discoveries
    -0.44
     various
    -0.44
     misplaced
    -0.44
     succes
    -0.44
     APM
    -0.43
     PIN
    -0.43
    POSITIVE LOGITS
     plutôt
    0.59
     inkább
    0.58
     wait
    0.52
    Rather
    0.52
    あえて
    0.51
    wait
    0.50
    ⟬
    0.50
     piuttosto
    0.50
     lieber
    0.50
     opt
    0.48
    Activations Density 0.518%

    No Known Activations