© 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. 3012
    Prev
    Next
    INDEX
    Explanations

    legal terminology related to contracts and warranties

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

    numbers and numerical sequences embedded in text.

    oai_token-act-pair · claude-4-5-haikuTriggered by @areeb0102
    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
     Horv
    -0.47
     Quig
    -0.47
     normal
    -0.47
    Slf
    -0.47
     Rugg
    -0.47
     you
    -0.46
     Krieger
    -0.45
     Rojas
    -0.45
    kwargs
    -0.44
     Hor
    -0.43
    POSITIVE LOGITS
    SBATCH
    0.59
     ſhould
    0.57
    SequentialGroup
    0.56
    Geplaatst
    0.54
     Shakspeare
    0.54
     canst
    0.54
     ſhall
    0.53
    AndEndTag
    0.53
     Shakira
    0.53
    DotNetBar
    0.52
    Activations Density 0.735%

    No Known Activations