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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 3-GEMMASCOPE-RES-16K
    6. 9448
    Prev
    Next
    INDEX
    Explanations

    references to programming constructs and components such as targets, generic types, and string handling methods

    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
     }^{(
    -0.56
    jona
    -0.54
    soort
    -0.53
     length
    -0.51
    сев
    -0.51
     }^{[
    -0.51
     recommandée
    -0.49
    aryen
    -0.49
    onViewCreated
    -0.48
    )^
    -0.48
    POSITIVE LOGITS
    WriteLiteral
    1.21
    MathML
    1.10
    FontStyle
    1.01
    ;#
    0.92
     Targeting
    0.85
     toString
    0.81
     StringBuilder
    0.81
     targets
    0.78
     Targets
    0.77
    target
    0.77
    Activations Density 0.010%

    No Known Activations