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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 22-GEMMASCOPE-RES-16K
    6. 10025
    Prev
    Next
    INDEX
    Explanations

    numerical data and statistics related to cancer research and treatment

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

    Numbers, especially years

    np_acts-logits-general · gemini-2.0-flash

    years with 9

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    MigrationBuilder
    -0.86
     GenerationType
    -0.61
    Rujuakan
    -0.60
    ngdoc
    -0.60
     resourceCulture
    -0.59
    NavController
    -0.59
     بيها
    -0.59
     مرئيه
    -0.58
    كويكب
    -0.58
    ModelAdmin
    -0.57
    POSITIVE LOGITS
    9
    1.24
    8
    0.90
    7
    0.72
    URLException
    0.63
     reciente
    0.56
    9
    0.53
     ActiveX
    0.52
     ninety
    0.51
     recent
    0.51
    6
    0.49
    Activations Density 0.158%

    No Known Activations