© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 2-GEMMASCOPE-RES-16K
    11. 16194
    Prev
    Next
    INDEX
    Explanations

    references to platforms or technological frameworks

    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
    jería
    -0.66
    entle
    -0.65
     suon
    -0.65
     hâte
    -0.65
     conservé
    -0.65
    حياته
    -0.63
    getExtras
    -0.63
    unzel
    -0.62
    RTLE
    -0.62
    inheritdoc
    -0.61
    POSITIVE LOGITS
     platform
    3.71
     platforms
    3.50
     Platform
    3.36
    platform
    3.33
     Platforms
    3.20
    Platform
    3.15
     PLATFORM
    3.10
     Plattform
    2.94
    platforms
    2.87
     plataforma
    2.78
    Activations Density 0.046%

    No Known Activations