© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 4-GEMMASCOPE-RES-16K
    6. 10766
    Prev
    Next
    INDEX
    Explanations

    formal academic terms and relevant references

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 4-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_4/width_16k/average_l0_124
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.hook_resid_post
    Hook Layer
    4
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    tvguidetime
    -0.93
     الحره
    -0.89
    sizeCache
    -0.80
    DeleteBehavior
    -0.76
     Roskov
    -0.72
     otomatig
    -0.72
     BoxDecoration
    -0.72
     незавершена
    -0.70
    CPtr
    -0.69
    +#+#
    -0.69
    POSITIVE LOGITS
    ById
    0.54
    stdlib
    0.50
     szóci
    0.48
     etc
    0.48
     fraction
    0.48
    fastjson
    0.46
     family
    0.44
    لينكات
    0.44
     send
    0.44
     solid
    0.44
    Activations Density 1.395%

    No Known Activations