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. 6-GEMMASCOPE-RES-16K
    6. 12252
    Prev
    Next
    INDEX
    Explanations

    references to database operations and code structures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 6-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_6/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.6.hook_resid_post
    Hook Layer
    6
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     XNUMX
    -0.75
    EndInit
    -0.68
    tagHelperRunner
    -0.65
    #+#
    -0.64
    lería
    -0.60
    extAlignment
    -0.59
     Roskov
    -0.58
    FlatAppearance
    -0.56
     Curitiba
    -0.54
     doubtnut
    -0.54
    POSITIVE LOGITS
    DataColumn
    0.74
    ForeignKey
    0.66
    LabelTagHelper
    0.64
    ConstraintMaker
    0.63
    RenderAtEndOf
    0.61
    IsMutable
    0.60
    makeConstraints
    0.58
    DataRow
    0.58
    ellido
    0.58
    HasForeignKey
    0.58
    Activations Density 0.029%

    No Known Activations