© 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. 3887
    Prev
    Next
    INDEX
    Explanations

    phrases related to information and details

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

    Comes after "about" or "on"

    np_acts-logits-general · gemini-2.0-flash

    information about

    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
    x
    -0.48
    he
    -0.46
     lini
    -0.44
    ur
    -0.43
     nobile
    -0.43
    c
    -0.41
    se
    -0.41
    с
    -0.41
    ž
    -0.40
    |
    -0.40
    POSITIVE LOGITS
    InjectAttribute
    1.34
     how
    1.28
    )':
    1.17
    addCriterion
    1.10
    )";
    1.03
    "])
    1.01
    исленность
    0.98
    DockStyle
    0.98
     cómo
    0.97
     hvordan
    0.97
    Activations Density 0.324%

    No Known Activations