© 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-2-2B
    4. Residual Stream - 16k
    5. 15-GEMMASCOPE-RES-16K
    6. 12975
    Prev
    Next
    INDEX
    Explanations

    elements related to service and customer satisfaction

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_15/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.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    til
    -0.44
    fü
    -0.41
     sở
    -0.41
     Nutz
    -0.41
    uzes
    -0.40
    lod
    -0.40
    inn
    -0.40
    攒
    -0.39
     inn
    -0.39
    pub
    -0.39
    POSITIVE LOGITS
     Efq
    0.99
     myſelf
    0.97
     ſta
    0.92
     houſe
    0.90
     purpoſe
    0.88
     faſt
    0.85
     domicilio
    0.85
     uſe
    0.82
     Majefty
    0.81
     uſed
    0.81
    Activations Density 0.174%

    No Known Activations