© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 10-GEMMASCOPE-RES-16K
    11. 7659
    Prev
    Next
    INDEX
    Explanations

    patterns or references to data organization and structure, possibly in statistical or hierarchical representations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_10/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.10.hook_resid_post
    Hook Layer
    10
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    elsen
    -0.47
    <eos>
    -0.46
     else
    -0.45
    tioners
    -0.45
    CASCADE
    -0.44
     [...]
    -0.44
    </td>
    -0.44
     væ
    -0.43
    __;
    -0.43
     ácidos
    -0.43
    POSITIVE LOGITS
    makeText
    0.89
    principalColumn
    0.83
    ScopeManager
    0.81
     المعيارى
    0.79
    ControllerAdvice
    0.77
    IVEREF
    0.76
    FormTagHelper
    0.75
    nvarchar
    0.74
     незавершена
    0.73
    Vidite
    0.70
    Activations Density 0.310%

    No Known Activations