© 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-2-9B
    4. Residual Stream - 16k
    5. 35-GEMMASCOPE-RES-16K
    6. 12766
    Prev
    Next
    INDEX
    Explanations

    concepts related to societal moral decline and the consequences of external threats to civilization

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 35-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_35/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.35.hook_resid_post
    Hook Layer
    35
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    verwijspagina
    -0.75
    Jeografia
    -0.54
     abstrato
    -0.50
    ppuden
    -0.49
    BagConstraints
    -0.48
    IsMutable
    -0.47
     raiſ
    -0.47
    ﷺ
    -0.46
     Jefus
    -0.45
    IContainer
    -0.45
    POSITIVE LOGITS
     collapse
    1.67
     collapsing
    1.36
     collapses
    1.29
     collapsed
    1.27
     Collapse
    1.27
     disaster
    1.23
    collapse
    1.22
    Collapse
    1.16
     disintegration
    1.16
     catastrophe
    1.09
    Activations Density 0.755%

    No Known Activations