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. 10-GEMMASCOPE-RES-16K
    6. 2956
    Prev
    Next
    INDEX
    Explanations

    mathematical concepts and terms related to functions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_10/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    EndContext
    -0.50
    cshtml
    -0.49
     regimes
    -0.49
     excitedly
    -0.48
    dann
    -0.48
    >>;
    -0.47
     academics
    -0.46
    nisse
    -0.46
    ulum
    -0.45
     admittedly
    -0.44
    POSITIVE LOGITS
     ModelExpression
    0.89
    XMLSchema
    0.83
     '\\;'
    0.76
     Audiodateien
    0.71
    ChildScrollView
    0.70
    AddHtmlAttribute
    0.69
     estimés
    0.68
    HomeAsUpEnabled
    0.66
    ensement
    0.65
     predeceased
    0.64
    Activations Density 1.284%

    No Known Activations