© 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. 16-GEMMASCOPE-RES-16K
    11. 4907
    Prev
    Next
    INDEX
    Explanations

    complex hierarchical structures and their relationships in data

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

    "bin" or "block" followed by descriptive words

    np_acts-logits-general · gemini-2.0-flash

    bin edges or centres, block diagonal or unit

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    lient
    -0.54
    )++;
    -0.52
    maca
    -0.50
    checkable
    -0.50
    iduous
    -0.49
     mad
    -0.47
    unya
    -0.47
    '];?>
    -0.47
    mach
    -0.47
    PerformLayout
    -0.46
    POSITIVE LOGITS
    ValueStyle
    0.69
    UnsafeEnabled
    0.67
     contiennent
    0.65
    ToScroll
    0.65
     Audiodateien
    0.64
    ごとに
    0.64
    ごと
    0.64
    IsContent
    0.63
     containing
    0.63
    ごとの
    0.61
    Activations Density 0.852%

    No Known Activations