© 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. 23-GEMMASCOPE-RES-16K
    6. 12715
    Prev
    Next
    INDEX
    Explanations

    references to statistical models and their properties

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 23-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_23/width_16k/average_l0_75
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.hook_resid_post
    Hook Layer
    23
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     snippetHide
    -0.76
     createSprite
    -0.63
     jadx
    -0.59
    שְׁ
    -0.58
    ViewFeatures
    -0.58
    QualifiedName
    -0.56
    localctx
    -0.56
    tableFuture
    -0.54
    hyrchwyd
    -0.52
     Klon
    -0.52
    POSITIVE LOGITS
     assumptions
    1.32
     assumed
    1.29
     assumption
    1.26
     Assumptions
    1.08
     assume
    1.07
    assumed
    1.06
     parameters
    1.05
    assumption
    1.01
    Assumption
    0.99
    Assumptions
    0.91
    Activations Density 2.273%

    No Known Activations