© 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. 35-GEMMASCOPE-RES-16K
    6. 14476
    Prev
    Next
    INDEX
    Explanations

    concepts related to mobile technology and research methodologies

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 35-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_35/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.35.hook_resid_post
    Hook Layer
    35
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     AssemblyCompany
    -0.44
    inaison
    -0.42
     الرياضيه
    -0.41
     zijne
    -0.39
    WithIOException
    -0.35
     виправивши
    -0.35
     réparer
    -0.35
    География
    -0.35
    órico
    -0.35
    Gambas
    -0.34
    POSITIVE LOGITS
     survey
    3.06
     surveys
    2.70
     Survey
    2.66
    survey
    2.58
    Survey
    2.58
     surveyed
    2.52
     SURVEY
    2.36
     Surveys
    2.36
     surveying
    2.25
    Surveys
    2.23
    Activations Density 0.661%

    No Known Activations