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. 25-GEMMASCOPE-RES-16K
    6. 3518
    Prev
    Next
    INDEX
    Explanations

    political roles and positions of individuals in relation to governance and administration

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 25-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.hook_resid_post
    Hook Layer
    25
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     surla
    -0.78
     defaultstate
    -0.73
    WireFormatLite
    -0.67
     Paglinawan
    -0.63
    Tikang
    -0.62
    WithIOException
    -0.56
     postIndex
    -0.55
    XmlAccessorType
    -0.54
     COURSE
    -0.53
    참고
    -0.52
    POSITIVE LOGITS
     special
    0.63
     Counsel
    0.62
     counsel
    0.60
     Under
    0.58
     acting
    0.58
    ENOMEM
    0.56
     Counselor
    0.56
     point
    0.56
     top
    0.55
    Counsel
    0.53
    Activations Density 0.354%

    No Known Activations