© 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. 5-GEMMASCOPE-RES-16K
    11. 5758
    Prev
    Next
    INDEX
    Explanations

    segments of code or structured data formats

    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
    Referencies
    -0.53
    Rhestr
    -0.51
    lotz
    -0.46
     (_)
    -0.44
    userInfo
    -0.43
    bės
    -0.43
    wellen
    -0.42
    itosti
    -0.42
     safely
    -0.42
     käytt
    -0.42
    POSITIVE LOGITS
     متعلقه
    0.91
    @",
    0.87
    GOTREF
    0.82
    ":[{
    0.81
     дописавши
    0.81
    $",
    0.80
    Попис
    0.79
    AccessorTable
    0.78
     tartalomajánló
    0.78
    Parcelize
    0.77
    Activations Density 0.190%

    No Known Activations