Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 17-GEMMASCOPE-RES-16K
    6. 5903
    Prev
    Next
    INDEX
    Explanations

    specific numerical statistics related to game performance

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 17-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_17/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.17.hook_resid_post
    Hook Layer
    17
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    исленность
    -0.56
    SBATCH
    -0.54
    principalColumn
    -0.51
    culosis
    -0.49
     חיצוניים
    -0.47
     vinted
    -0.46
     politiet
    -0.45
    sidemargin
    -0.44
     createSlice
    -0.43
     politie
    -0.43
    POSITIVE LOGITS
     defense
    0.75
     scoring
    0.72
     scored
    0.72
     Scoring
    0.69
     offense
    0.69
    aktery
    0.67
     average
    0.66
    scoring
    0.66
     score
    0.65
    Scoring
    0.65
    Activations Density 0.149%

    No Known Activations