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. 14-GEMMASCOPE-RES-16K
    6. 10613
    Prev
    Next
    INDEX
    Explanations

    various forms of notation and mathematical operators

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 14-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_14/width_16k/average_l0_84
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.14.hook_resid_post
    Hook Layer
    14
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     a
    -0.45
    اهم
    -0.45
     co
    -0.44
     “
    -0.42
     {}));
    -0.42
     R
    -0.42
    省市镇
    -0.41
     mass
    -0.41
     U
    -0.41
     r
    -0.41
    POSITIVE LOGITS
     itſelf
    1.01
    ),”
    0.97
     myſelf
    0.94
    SourceChecksum
    0.93
    )
    0.90
     themſelves
    0.89
    tvguidetime
    0.86
    )،
    0.85
     ...)
    0.85
     purpoſe
    0.84
    Activations Density 1.325%

    No Known Activations