© 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 - 16k
    9. 34-GEMMASCOPE-RES-16K
    11. 11354
    Prev
    Next
    INDEX
    Explanations

    patterns or indicators related to numerical data and identifiers

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 34-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_34/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.34.hook_resid_post
    Hook Layer
    34
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    AntiForgeryToken
    -0.47
     <<<<<<<<<<<<<<
    -0.40
    iD
    -0.38
    MigrationBuilder
    -0.37
    fA
    -0.35
    SerializeField
    -0.35
    tB
    -0.35
    QI
    -0.35
     IA
    -0.35
    ')}}
    -0.34
    POSITIVE LOGITS
     transfieras
    0.59
     surla
    0.51
     textColor
    0.50
     vnnd
    0.48
    txtName
    0.46
    zsef
    0.46
     skb
    0.46
     IFTT
    0.45
     greu
    0.45
    GLenum
    0.43
    Activations Density 0.994%

    No Known Activations