© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 15-GEMMASCOPE-RES-16K
    11. 5378
    Prev
    Next
    INDEX
    Explanations

    general phrases or sequences of non-specific characters, likely indicating formatting or placeholder text

    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
    uitton
    -0.77
    '}),
    -0.73
    oinette
    -0.71
    fordshire
    -0.68
    rédients
    -0.67
     iſt
    -0.67
    WEBPACK
    -0.67
    SBATCH
    -0.67
     createSlice
    -0.66
    Espèce
    -0.66
    POSITIVE LOGITS
    <eos>
    0.62
     etc
    0.60
    ↵↵
    0.58
     مشين
    0.55
    etc
    0.51
    AndEndTag
    0.50
    ↵↵↵
    0.50
    ↵
    0.46
    PerformLayout
    0.46
     Afraid
    0.45
    Activations Density 0.713%

    No Known Activations