© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 131k
    9. 20-GEMMASCOPE-RES-131K
    11. 105610
    Prev
    Next
    INDEX
    Explanations

    punctuation marks, particularly semicolons and colons

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_131k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    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
     againſt
    -0.45
     وتسجيلات
    -0.44
    RTHOOK
    -0.41
     takže
    -0.38
    发表于
    -0.35
     himſelf
    -0.35
     možná
    -0.35
     оригіналу
    -0.35
     bestimmten
    -0.33
     beina
    -0.33
    POSITIVE LOGITS
    uxxxx
    0.60
    .*")]
    0.60
    Personensuche
    0.59
    EDEFAULT
    0.58
     Klu
    0.56
    ፩
    0.56
    triangleq
    0.54
    Referències
    0.53
    >--}}
    0.53
    protoimpl
    0.52
    Activations Density 0.031%

    No Known Activations