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. 8276
    Prev
    Next
    INDEX
    Explanations

    terms related to governance and regulatory frameworks

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

    government bodies or international organizations

    np_acts-logits-general · gemini-2.0-flash

    official communication and reports

    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
    dafx
    -0.65
     كمان
    -0.57
    يًا
    -0.54
    Santis
    -0.49
    GraphicsUnit
    -0.49
    allowNull
    -0.48
    Карьера
    -0.48
     troviamo
    -0.47
    getMenuInflater
    -0.47
    Segoe
    -0.47
    POSITIVE LOGITS
     Exacts
    0.64
    ItemLayout
    0.62
     Reverso
    0.60
     חיצוניים
    0.59
     Secretariat
    0.59
     chapeau
    0.58
     Replies
    0.58
     Parties
    0.58
     Member
    0.58
    ItemBackground
    0.57
    Activations Density 0.142%

    No Known Activations