© 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. 2927
    Prev
    Next
    INDEX
    Explanations

    terms related to crime and legal issues

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    terms related to crime, government regulation, and political activism

    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
     للاسماء
    -0.59
    ConstraintMaker
    -0.54
    ory
    -0.53
    ations
    -0.51
    orial
    -0.51
    ational
    -0.50
    jspx
    -0.50
     OFDb
    -0.49
     Normdatei
    -0.49
    inib
    -0.48
    POSITIVE LOGITS
    ed
    1.19
    ever
    1.10
    ette
    1.07
    ists
    1.04
    ities
    1.04
    ist
    1.03
    ised
    1.02
    ized
    1.00
    ee
    0.93
    i
    0.93
    Activations Density 1.819%

    No Known Activations