© 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. 19-GEMMASCOPE-RES-16K
    11. 11055
    Prev
    Next
    INDEX
    Explanations

    terms related to modulation and comparative analysis 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 @ 19-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_19/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.hook_resid_post
    Hook Layer
    19
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    iastes
    -0.60
    IVEREF
    -0.58
    かつ
    -0.56
    roix
    -0.56
    refour
    -0.56
    respective
    -0.55
    fycat
    -0.54
    withstanding
    -0.53
    pexpr
    -0.53
    nteral
    -0.52
    POSITIVE LOGITS
     which
    2.81
    which
    2.46
     WHICH
    1.94
     who
    1.76
    Which
    1.75
     Which
    1.75
     whose
    1.59
     который
    1.51
    whose
    1.47
    ซึ่ง
    1.44
    Activations Density 1.142%

    No Known Activations