© 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. 18-GEMMASCOPE-RES-16K
    11. 9762
    Prev
    Next
    INDEX
    Explanations

    biochemical terms related to cardiac function

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

    Mathematical/scientific notation or symbols

    np_acts-logits-general · gemini-2.0-flash

    failure

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     MainAxisSize
    -0.79
    новништво
    -0.68
    contentLoaded
    -0.68
    stdc
    -0.66
    tvguidetime
    -0.65
    LookAnd
    -0.64
    ьаж
    -0.63
    PMailer
    -0.60
    ToScroll
    -0.60
     GeoNames
    -0.59
    POSITIVE LOGITS
     failure
    1.50
     Failure
    1.37
    Failure
    1.33
    failure
    1.28
     failing
    1.14
     failures
    1.07
     FAILURE
    1.02
     Failing
    1.01
    Failing
    0.98
     wrong
    0.94
    Activations Density 0.332%

    No Known Activations