© 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. 17-GEMMASCOPE-RES-16K
    11. 11238
    Prev
    Next
    INDEX
    Explanations

    programming language constructs related to data attributes and shadow computations

    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
    >{"
    -0.84
    afone
    -0.74
    ("")]
    -0.73
     tartalomajánló
    -0.73
    ]=="
    -0.72
    ogast
    -0.69
    <>();
    -0.69
     *__
    -0.68
    */].
    -0.68
    ]='\
    -0.67
    POSITIVE LOGITS
    (
    1.00
     (
    0.72
     InputDecoration
    0.64
     BoxDecoration
    0.60
    mybatisplus
    0.58
     estekak
    0.58
     with
    0.57
    （
    0.57
     للاسماء
    0.50
    ,
    0.50
    Activations Density 0.207%

    No Known Activations