© 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. 40-GEMMASCOPE-RES-16K
    11. 5602
    Prev
    Next
    INDEX
    Explanations

    repeated instances of punctuation marks, specifically periods

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 40-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_40/width_16k/average_l0_125
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.40.hook_resid_post
    Hook Layer
    40
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     priv
    -0.35
     print
    -0.34
     contend
    -0.33
     rec
    -0.33
     place
    -0.32
     ref
    -0.31
    算
    -0.31
     detail
    -0.31
     Sach
    -0.29
     taget
    -0.29
    POSITIVE LOGITS
    google
    0.83
    fasterxml
    0.79
    amazonaws
    0.71
     GOOGLE
    0.60
    github
    0.60
    squareup
    0.59
    badlogic
    0.58
    ftagPool
    0.58
    sun
    0.58
     мәкал
    0.57
    Activations Density 0.072%

    No Known Activations