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. 22-GEMMASCOPE-RES-16K
    6. 7992
    Prev
    Next
    INDEX
    Explanations

    records related to athletic performance and achievements

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

    following "for" or related to goals/scoring

    np_acts-logits-general · gemini-2.0-flash

    goals, scores, records

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ercito
    -0.54
    hysema
    -0.50
    icali
    -0.48
    ADATA
    -0.47
    hmac
    -0.47
    ]")]
    -0.47
    uticos
    -0.47
    ageo
    -0.47
     Derfor
    -0.46
    zessin
    -0.46
    POSITIVE LOGITS
     scoring
    1.77
     scored
    1.63
     score
    1.58
     Scoring
    1.54
    Scoring
    1.49
    scoring
    1.47
    scored
    1.39
     scores
    1.38
    score
    1.36
     goals
    1.30
    Activations Density 0.404%

    No Known Activations