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

    Neuronpedia

    APICircuit 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. 5-GEMMASCOPE-RES-16K
    6. 2302
    Prev
    Next
    INDEX
    Explanations

    proper names and familial relationships

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.5.hook_resid_post
    Hook Layer
    5
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     CreateTagHelper
    -0.73
     kasarigan
    -0.72
    ISupport
    -0.67
    aarrggbb
    -0.66
    MigrationBuilder
    -0.64
    writerow
    -0.60
    EndInit
    -0.58
    UrlResolution
    -0.57
    ArrowToggle
    -0.57
    ptonshire
    -0.56
    POSITIVE LOGITS
    feira
    0.47
    risa
    0.47
    FOLIO
    0.47
    EndContext
    0.46
    platte
    0.45
    hões
    0.45
     AppCompatTheme
    0.45
    insegna
    0.44
    ^(@)
    0.44
    cipais
    0.42
    Activations Density 0.274%

    No Known Activations