© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 24-GEMMASCOPE-RES-16K
    11. 4817
    Prev
    Next
    INDEX
    Explanations

    programming syntax elements and constructs

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

    Code snippets, especially returns and conditionals

    np_acts-logits-general · gemini-2.0-flash

    ordinary, graphs, in

    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
    <unused62>
    -0.41
    ​​
    -0.41
    "
    -0.40
    <unused61>
    -0.38
    </em>
    -0.38
     فريبيس
    -0.37
    '
    -0.37
    <unused63>
    -0.37
     Процитовано
    -0.36
    .
    -0.35
    POSITIVE LOGITS
     Theſe
    0.94
     Monfieur
    0.83
     Efq
    0.76
     Beſ
    0.75
     purpoſe
    0.71
    الإنجليزية
    0.71
    DllImport
    0.71
    imarães
    0.69
    jectures
    0.69
    ellite
    0.68
    Activations Density 0.130%

    No Known Activations