© 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 - 65k
    5. 13-GEMMASCOPE-RES-65K
    6. 14870
    Prev
    Next
    INDEX
    Explanations

    beginning phrases or sections of text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 13-gemmascope-res-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_13/width_65k/average_l0_75
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    Data Type
    float32
    Hook Name
    blocks.13.hook_resid_post
    Hook Layer
    13
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     فريبيس
    -0.72
    DockStyle
    -0.68
    InitVars
    -0.59
    phir
    -0.55
     صوتيه
    -0.55
    }{*}{}
    -0.55
     Pinn
    -0.54
    hdashline
    -0.54
    piracy
    -0.53
    --)
    
    -0.53
    POSITIVE LOGITS
    AndroidJUnit
    0.68
     MonoBehaviour
    0.66
    !*\
    0.59
    interopRequire
    0.58
    usermodel
    0.57
    ⓧ
    0.56
     DialogResult
    0.56
    /*
    0.55
    UnusedPrivate
    0.55
     DBNull
    0.54
    Activations Density 0.007%

    No Known Activations