© 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-IT
    7. Residual Stream - 131k
    9. 31-GEMMASCOPE-RES-131K
    11. 24528
    Prev
    Next
    INDEX
    Explanations

    phrases related to intentions and efforts within organizational contexts

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

    promising future

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 31-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_31/width_131k/average_l0_109
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    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
    attuale
    -0.46
    resave
    -0.40
    既に
    -0.40
     esist
    -0.38
    引き続き
    -0.37
    __(/*!
    -0.37
    苦手な
    -0.37
    すでに
    -0.37
    onymous
    -0.37
     rincón
    -0.37
    POSITIVE LOGITS
     promising
    1.22
     promise
    0.93
     promised
    0.87
     promises
    0.86
     promis
    0.82
     promet
    0.82
     optimism
    0.81
     excitement
    0.81
     hoped
    0.80
     seemed
    0.79
    Activations Density 0.091%

    No Known Activations