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-2-2B
    4. Residual Stream - 16k
    5. 12-GEMMASCOPE-RES-16K
    6. 2876
    Prev
    Next
    INDEX
    Explanations

    terms related to encouragement and support

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    id
    -0.78
    zio
    -0.73
     Babies
    -0.69
    delli
    -0.68
    io
    -0.68
    as
    -0.67
    t
    -0.66
     half
    -0.66
    fi
    -0.65
    n
    -0.65
    POSITIVE LOGITS
     encouraged
    1.51
     Encourage
    1.39
    couraged
    1.39
     encourages
    1.36
    Encourage
    1.36
     encourage
    1.36
     encouragement
    1.35
     encourag
    1.30
    encouragement
    1.27
     encor
    1.20
    Activations Density 0.121%

    No Known Activations