© 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. 25-GEMMASCOPE-RES-16K
    11. 12358
    Prev
    Next
    INDEX
    Explanations

    terms related to risks and challenges in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 25-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.hook_resid_post
    Hook Layer
    25
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     समीक्षक
    -0.68
    züglich
    -0.54
     Strand
    -0.54
    ilstein
    -0.54
    __(/*!
    -0.53
    irected
    -0.53
     विश्वसनीय
    -0.51
    ịp
    -0.51
    andangan
    -0.50
    InSection
    -0.48
    POSITIVE LOGITS
     involved
    1.61
    involved
    1.38
     Involved
    1.24
     INVOLVED
    1.17
     entailed
    1.13
     attached
    1.13
     associated
    1.11
     inherent
    1.10
    inher
    0.95
     involucrados
    0.92
    Activations Density 0.474%

    No Known Activations