Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit 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. 5-GEMMASCOPE-RES-16K
    6. 13193
    Prev
    Next
    INDEX
    Explanations

    copyright statements and legal conditions regarding software

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.5.hook_resid_post
    Hook Layer
    5
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    цима
    -0.52
     prisonniers
    -0.47
     itulah
    -0.47
     demikian
    -0.47
     témoignages
    -0.47
     dataSet
    -0.46
     jesu
    -0.45
    protoimpl
    -0.45
     pères
    -0.43
    sqrt
    -0.43
    POSITIVE LOGITS
    VersionUID
    2.29
    
    1.44
    ruptedException
    1.35
    Skocz
    1.08
    cshtml
    1.04
    TabIndex
    1.04
    numerusform
    1.04
    новништво
    1.00
    </thead>
    0.99
    uxxxx
    0.99
    Activations Density 0.021%

    No Known Activations