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. 5427
    Prev
    Next
    INDEX
    Explanations

    the presence of metadata or structural components in text

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

    Code snippets or technical documentation

    np_acts-logits-general · gemini-2.0-flash

    figure references and legal context

    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
    <eos>
    -2.36
     […]
    -0.62
    Portály
    -0.56
    منبع
    -0.50
    ","
    -0.49
    Portail
    -0.46
    -0.45
    <unused63>
    -0.45
    loe
    -0.45
    fini
    -0.45
    POSITIVE LOGITS
    帖最后由
    0.86
    Hochspringen
    0.80
    WebVitals
    0.74
    ngdoc
    0.73
     Saltar
    0.73
    IntoConstraints
    0.72
    SourceChecksum
    0.71
     DBNull
    0.71
    findpost
    0.70
    Бахар
    0.68
    Activations Density 0.083%

    No Known Activations