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. 21-GEMMASCOPE-RES-16K
    6. 7536
    Prev
    Next
    INDEX
    Explanations

    HTML tags and structure in the document

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    клопе
    -0.71
    Koordinaten
    -0.53
     grate
    -0.53
    Източници
    -0.52
    gew
    -0.50
     كومونز
    -0.49
     Barbosa
    -0.49
    ();)
    -0.49
    IndentedString
    -0.49
     tendons
    -0.48
    POSITIVE LOGITS
    Autoritní
    0.76
     CreateTagHelper
    0.58
     propOrder
    0.56
    SharedDtor
    0.56
     TestBed
    0.54
    letterSpacing
    0.53
    AxisAlignment
    0.52
    complexType
    0.52
    Билгалдахарш
    0.49
     autorytatywna
    0.49
    Activations Density 0.335%

    No Known Activations