© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 24-GEMMASCOPE-RES-16K
    6. 1356
    Prev
    Next
    INDEX
    Explanations

    any mentions of contact information or communication methods

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

    Tokens appearing before URLs or emails

    np_acts-logits-general · gemini-2.0-flash

    URLs, email addresses, and phone numbers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_24/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 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
     cherchés
    -0.59
    UrlResolution
    -0.40
     nemlig
    -0.40
    Transkript
    -0.38
     validamos
    -0.38
    hafen
    -0.37
    Bronnen
    -0.36
    Referencie
    -0.35
    InputBorder
    -0.34
     hObject
    -0.34
    POSITIVE LOGITS
     препратки
    0.56
     visiting
    0.43
     Alexa
    0.42
    inier
    0.40
    ChartData
    0.40
    writeValue
    0.40
     ngang
    0.40
    gentle
    0.40
     download
    0.40
     visit
    0.40
    Activations Density 0.178%

    No Known Activations