© 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. 18-GEMMASCOPE-RES-16K
    11. 6792
    Prev
    Next
    INDEX
    Explanations

    terms related to data analysis and visualization

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Sections or divisions (bins, frames, slices)

    np_acts-logits-general · gemini-2.0-flash

    bin, plot, frame, slice, turn, class

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     hại
    -0.65
     للمعارف
    -0.64
    ніципалі
    -0.57
    wną
    -0.56
     Италијани
    -0.56
     MaterialApp
    -0.55
    ]++;
    -0.53
     Su
    -0.52
    addCriterion
    -0.51
    )++;
    -0.51
    POSITIVE LOGITS
    number
    0.67
     Audiodateien
    0.64
    ละ
    0.64
     number
    0.63
    CompleteListener
    0.63
    SBATCH
    0.59
     numberOfRows
    0.58
    ごとの
    0.58
     contiennent
    0.58
     containing
    0.58
    Activations Density 0.751%

    No Known Activations