© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 3-GEMMASCOPE-RES-16K
    6. 1824
    Prev
    Next
    INDEX
    Explanations

    time indicators and related data structures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     eventdata
    -0.60
     CreateTagHelper
    -0.60
    {#
    -0.56
     harem
    -0.55
     Dijo
    -0.55
     disambiguazione
    -0.53
    noinspection
    -0.53
    CFR
    -0.53
    brä
    -0.53
    brot
    -0.52
    POSITIVE LOGITS
    LabelTagHelper
    0.74
    PullParser
    0.59
    migrationBuilder
    0.57
    fromnode
    0.53
    GOTREF
    0.51
    GeoNames
    0.49
    IContainer
    0.49
    vábbi
    0.49
    捧
    0.48
     unin
    0.48
    Activations Density 0.263%

    No Known Activations