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. 24-GEMMASCOPE-RES-16K
    6. 14173
    Prev
    Next
    INDEX
    Explanations

    references to consumer rights and protections

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

    Credit checks and reports

    np_acts-logits-general · gemini-2.0-flash

    credit reports and background checks

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ValueStyle
    -0.67
    XmlAccessType
    -0.58
     onOptions
    -0.56
    makeText
    -0.55
    -};
    -0.53
    principalColumn
    -0.53
     ब्रेकडाउन
    -0.53
     paddy
    -0.53
    Hamlet
    -0.52
     Tapas
    -0.52
    POSITIVE LOGITS
     background
    1.13
     credit
    1.04
     Background
    0.96
     antecedentes
    0.91
    background
    0.89
     Credit
    0.87
    Background
    0.86
    credit
    0.83
     BACKGROUND
    0.81
    Credit
    0.79
    Activations Density 0.247%

    No Known Activations