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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 15-GEMMASCOPE-RES-16K
    6. 3886
    Prev
    Next
    INDEX
    Explanations

    specific programming syntax and structure

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_15/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     GenerationType
    -0.69
     doInBackground
    -0.59
    gane
    -0.57
    الحياه
    -0.56
     TextAppearance
    -0.54
    orestation
    -0.53
    shafen
    -0.53
    WebElementEntity
    -0.53
    Dispatchers
    -0.53
    SequentialGroup
    -0.53
    POSITIVE LOGITS
     justice
    0.46
     juges
    0.43
     esternos
    0.43
     unità
    0.43
    Justice
    0.43
    James
    0.42
    j
    0.42
     JAM
    0.42
    좌
    0.41
     Jornal
    0.41
    Activations Density 0.185%

    No Known Activations