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. 7965
    Prev
    Next
    INDEX
    Explanations

    references to secrecy and hidden information

    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
    Rptr
    -0.70
     MainAxisSize
    -0.69
     autorytatywna
    -0.61
    MigrationBuilder
    -0.61
     CreateTagHelper
    -0.60
    migrationBuilder
    -0.60
    ंदीखरीदारी
    -0.57
    //
    -0.54
    EndContext
    -0.53
    principalColumn
    -0.52
    POSITIVE LOGITS
     longer
    1.57
     forever
    1.35
     longest
    1.33
    longer
    1.22
     indefinitely
    1.19
     Longer
    1.12
    forever
    1.12
     FOREVER
    1.03
     awhile
    1.02
    Longer
    1.02
    Activations Density 0.343%

    No Known Activations