Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 25-GEMMASCOPE-RES-16K
    6. 8661
    Prev
    Next
    INDEX
    Explanations

    proper nouns associated with locations and religious or cultural institutions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 25-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.hook_resid_post
    Hook Layer
    25
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    providedIn
    -0.84
    awtextra
    -0.72
    MigrationBuilder
    -0.67
    ReusableCell
    -0.63
     []:
    -0.60
    GraphicsUnit
    -0.59
    GEBURTSDATUM
    -0.58
    لينكات
    -0.57
    RegressionTest
    -0.55
    Rhestr
    -0.55
    POSITIVE LOGITS
    Cyfeiriadau
    0.59
     Parrish
    0.57
    paro
    0.57
     Parish
    0.53
     Church
    0.53
    Reprints
    0.48
     CHURCH
    0.47
    encial
    0.47
    assumption
    0.46
     kertas
    0.46
    Activations Density 0.239%

    No Known Activations