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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 16-GEMMASCOPE-RES-16K
    6. 14690
    Prev
    Next
    INDEX
    Explanations

    monetary or financial symbols and their relationships

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

    Text within dollar signs and code snippets

    np_acts-logits-general · gemini-2.0-flash

    confidence intervals

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     National
    -0.54
     home
    -0.53
     Go
    -0.52
    лық
    -0.51
     '
    -0.49
     where
    -0.48
     Der
    -0.48
    人之
    -0.48
     Tr
    -0.48
     C
    -0.48
    POSITIVE LOGITS
    BeginContext
    0.89
    ConstraintMaker
    0.89
     NSCoder
    0.81
    IntoConstraints
    0.78
    URLException
    0.76
     defaultstate
    0.74
    AROUND
    0.72
    expandindo
    0.72
     Roskov
    0.71
    VersionUID
    0.71
    Activations Density 0.899%

    No Known Activations