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. 11-GEMMASCOPE-RES-16K
    6. 6896
    Prev
    Next
    INDEX
    Explanations

    escape sequences or control characters

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 11-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_11/width_16k/average_l0_80
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Hook Layer
    11
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     يتيمه
    -1.01
     layui
    -0.84
     Hagen
    -0.81
    PMailer
    -0.81
     estimés
    -0.79
    دانشنامهٔ
    -0.78
     transfieras
    -0.78
    ajin
    -0.78
    ništvo
    -0.78
     Goldberg
    -0.78
    POSITIVE LOGITS
    \
    1.23
     \
    0.97
    ))\
    0.95
    </tr>
    0.94
    <h3>
    0.90
    <tbody>
    0.88
    ).\
    0.87
    '\
    0.86
    %\
    0.85
    ;\
    0.84
    Activations Density 0.008%

    No Known Activations