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. 20-GEMMASCOPE-RES-16K
    6. 5262
    Prev
    Next
    INDEX
    Explanations

    quotes and dialogue in the text

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

    Attribution after a quote

    np_acts-logits-general · gemini-2.0-flash

    reporting verbs and direct speech

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    UrlResolution
    -0.59
    ölkerung
    -0.47
     ddelweddau
    -0.46
    ificação
    -0.44
     Iggy
    -0.42
     Veuillez
    -0.42
     ourselves
    -0.41
    的话
    -0.41
    uldade
    -0.41
    چار
    -0.41
    POSITIVE LOGITS
     he
    1.21
     said
    1.13
    said
    1.02
     she
    0.98
     katanya
    0.84
    WithIOException
    0.83
     they
    0.82
     resourceCulture
    0.82
     noqa
    0.77
    帖最后由
    0.77
    Activations Density 0.041%

    No Known Activations