© 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-2-9B-IT
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 4339
    Prev
    Next
    INDEX
    Explanations

    specific scientific terminology and terms related to studies, experiments, or data analysis

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

    after technical terms or variables

    np_acts-logits-general · gemini-2.0-flash

    biological and medical terminology

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ListItemIcon
    -0.50
    makeText
    -0.49
    tagHelperRunner
    -0.47
     المعيارى
    -0.47
     calendriers
    -0.46
    AndEndTag
    -0.44
     Italijanski
    -0.40
    ########.
    -0.40
     GenerationType
    -0.38
     TextFormField
    -0.38
    POSITIVE LOGITS
    extAlignment
    0.49
    enterOuterAlt
    0.44
    الحياه
    0.44
    principalTable
    0.44
    adpleegd
    0.43
     CURIAM
    0.42
     tarifas
    0.42
    KommentareTeilen
    0.42
     argint
    0.41
    RenderAtEndOf
    0.41
    Activations Density 1.049%

    No Known Activations