© 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. 31-GEMMASCOPE-RES-16K
    6. 9727
    Prev
    Next
    INDEX
    Explanations

    words related to force or compulsion

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    the word "force" and its adjacent tokens, particularly in compound phrases like "force-air" or "forced-air".

    oai_token-act-pair · claude-4-5-haikuTriggered by @emiglarou
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 31-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_31/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.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    marginHorizontal
    -0.35
    whatsapp
    -0.33
    WAII
    -0.31
    veston
    -0.30
    StatusOK
    -0.29
    raszamy
    -0.28
    ngOnInit
    -0.28
    щет
    -0.28
    kt
    -0.27
    Obituary
    -0.27
    POSITIVE LOGITS
     Force
    0.82
     FORCE
    0.80
     majeure
    0.79
    force
    0.77
    Force
    0.74
     force
    0.73
    FORCE
    0.68
     Maje
    0.68
     Normdatei
    0.67
    forced
    0.66
    Activations Density 0.123%

    No Known Activations