© 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. 17-GEMMASCOPE-RES-16K
    6. 4974
    Prev
    Next
    INDEX
    Explanations

    phrases that indicate a focus or concentration on specific topics or issues

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 17-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_17/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.17.hook_resid_post
    Hook Layer
    17
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ʒ
    -0.52
    ci
    -0.49
    Accessed
    -0.48
    꿀
    -0.48
     supplémentaires
    -0.45
    kijk
    -0.45
    нева
    -0.44
     nime
    -0.44
     previo
    -0.42
     inferred
    -0.42
    POSITIVE LOGITS
    OGND
    0.94
    GraphicsUnit
    0.93
    ViewFeatures
    0.89
     nahilalakip
    0.84
    存于互联网档案馆
    0.81
    Portail
    0.79
    +#+#
    0.79
    RTEE
    0.78
     disambiguazione
    0.78
    ponses
    0.77
    Activations Density 0.212%

    No Known Activations