© 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. 2-GEMMASCOPE-RES-16K
    6. 1976
    Prev
    Next
    INDEX
    Explanations

    references to specific works or contributions by individuals, particularly in a review context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_2/width_16k/average_l0_141
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     المعيارى
    -0.93
     فريبيس
    -0.81
    windowFixed
    -0.81
    bootstrapcdn
    -0.80
     itſelf
    -0.78
    mybatisplus
    -0.77
     crdi
    -0.75
    addCriterion
    -0.74
     MessageBoxIcon
    -0.73
     iſt
    -0.72
    POSITIVE LOGITS
    *
    2.08
     *
    1.37
    *,
    1.31
    *.
    1.21
    *)
    1.15
    *),
    1.14
    .*
    1.13
    *"
    1.07
    )*
    1.05
    *);
    1.03
    Activations Density 0.479%

    No Known Activations