© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 10966
    Prev
    Next
    INDEX
    Explanations

    references to licenses and legal conditions related to software distribution

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

    Tokens before closing parenthesis

    np_acts-logits-general · gemini-2.0-flash

    license, estoppel, feed, .txt, or tree

    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
     (
    -0.59
    -
    -0.55
     h
    -0.53
    وفير
    -0.52
     and
    -0.50
     for
    -0.48
     by
    -0.48
    +
    -0.47
     Punkt
    -0.47
     stand
    -0.46
    POSITIVE LOGITS
     estekak
    0.99
    verwijspagina
    0.98
     الحره
    0.98
    Personensuche
    0.97
    ⓧ
    0.95
     CreateTagHelper
    0.94
     المعيارى
    0.94
    OGND
    0.90
     تانيه
    0.85
     فريبيس
    0.83
    Activations Density 0.243%

    No Known Activations