© 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. 25-GEMMASCOPE-RES-16K
    6. 12868
    Prev
    Next
    INDEX
    Explanations

    positive descriptors of individuals, emphasizing their character traits and achievements

    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
    •Steering evals
    praise

    No Comments

    Negative Logits
    MemoryWarning
    -0.81
    Tikang
    -0.67
    ArgsConstructor
    -0.59
    ThroughAttribute
    -0.59
     NavController
    -0.55
    issage
    -0.53
     كومونز
    -0.52
    ลม
    -0.51
     חיצוניים
    -0.50
    ради
    -0.50
    POSITIVE LOGITS
     person
    0.81
     individual
    0.81
     human
    0.70
    individual
    0.69
    KommentareTeilen
    0.68
     pribadi
    0.65
     INDIVIDUAL
    0.65
    individu
    0.64
     للاسماء
    0.63
     conversational
    0.63
    Activations Density 0.244%

    No Known Activations