© 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. 8-GEMMASCOPE-RES-16K
    6. 2208
    Prev
    Next
    INDEX
    Explanations

    elements and steps related to cooking or preparation instructions, particularly temperatures and settings

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 8-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_8/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.hook_resid_post
    Hook Layer
    8
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    mybatisplus
    -0.61
    <bos>
    -0.55
    gården
    -0.54
     comen
    -0.48
     van
    -0.47
    parian
    -0.46
    spoon
    -0.46
    behaved
    -0.45
    NCBI
    -0.45
     onSave
    -0.44
    POSITIVE LOGITS
     وتسجيلات
    0.97
     Theſe
    0.81
     raiſ
    0.73
     Reſ
    0.71
     fevere
    0.70
     theſe
    0.69
     pleaſure
    0.69
     faſt
    0.69
     ſch
    0.68
     MaterialApp
    0.68
    Activations Density 0.392%

    No Known Activations