Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 2498
    Prev
    Next
    INDEX
    Explanations

    concepts related to solidarity and community support

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

    solidarity, synergy, and fellowship

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Gobernador
    -0.43
    Eisen
    -0.36
     russes
    -0.35
    TEntity
    -0.34
     Jepang
    -0.34
    MenuInflater
    -0.34
     quoi
    -0.34
     horribly
    -0.34
    }}^
    -0.33
     MutableLiveData
    -0.33
    POSITIVE LOGITS
     Solidarity
    0.98
     solidarity
    0.97
     solidarité
    0.96
     solidaridad
    0.84
     solidari
    0.80
     solidar
    0.73
     fraternal
    0.70
     lenker
    0.70
    tagHelperRunner
    0.69
    arity
    0.68
    Activations Density 0.007%

    No Known Activations