© 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. 20-GEMMASCOPE-RES-16K
    11. 3921
    Prev
    Next
    INDEX
    Explanations

    instances of references to specific documents or evidence and their interpretations

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

    academic or research-related terminology and phrases.

    oai_token-act-pair · claude-3-5-haiku-20241022Triggered by @neilrathi
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_16k/average_l0_68
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Ber
    -0.28
     signed
    -0.28
     Appel
    -0.28
    ter
    -0.28
     Freunden
    -0.27
     himo
    -0.27
     Kear
    -0.27
     Baron
    -0.26
    </td>
    -0.26
     voulu
    -0.26
    POSITIVE LOGITS
    الحياه
    0.77
     invokingState
    0.74
    TypedDataSet
    0.70
     nahilalakip
    0.70
    fromnode
    0.68
    Gambas
    0.66
    ⟬
    0.66
     uLocal
    0.66
    UVWXYZ
    0.66
    CppMethod
    0.66
    Activations Density 2.815%

    No Known Activations