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

    Neuronpedia

    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. 4591
    Prev
    Next
    INDEX
    Explanations

    comparisons and contrasts in data or results

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    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
     propOrder
    -0.52
    Dermott
    -0.37
    +#+#
    -0.34
    BIÉN
    -0.34
     tục
    -0.31
    LLocation
    -0.31
    YGON
    -0.31
    Cent
    -0.31
     genom
    -0.30
     dienst
    -0.30
    POSITIVE LOGITS
     versus
    1.48
     vs
    1.43
    versus
    1.27
     Versus
    1.24
     Vs
    1.17
    Versus
    1.14
     compared
    1.12
    vs
    1.06
     dibandingkan
    1.03
     VS
    1.02
    Activations Density 0.504%

    No Known Activations