© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 4-GEMMASCOPE-RES-16K
    11. 12842
    Prev
    Next
    INDEX
    Explanations

    well-defined instructions or operations that involve careful handling or manipulation of processes

    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
     ujednoznacz
    -0.57
    principalTable
    -0.55
     initComponents
    -0.55
     فريبيس
    -0.55
    toBeTruthy
    -0.52
     NUKAT
    -0.52
     behulp
    -0.51
    wyczaj
    -0.50
     come
    -0.50
    GeoNames
    -0.50
    POSITIVE LOGITS
    })));
    0.71
    noinspection
    0.59
    )))),
    0.57
    AutoScaleMode
    0.57
    帖最后由
    0.55
    ISupport
    0.55
    ViewFeatures
    0.53
    ={({
    0.53
    bitat
    0.51
     становника
    0.51
    Activations Density 0.749%

    No Known Activations