© 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. 20-GEMMASCOPE-RES-16K
    11. 831
    Prev
    Next
    INDEX
    Explanations

    references to numerical values, particularly maximums and minimums

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

    The token "Max" and its variations

    np_acts-logits-general · gemini-2.0-flash

    Max-Planck, Max Barry, Maxilla

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     AssemblyCompany
    -0.77
    OGND
    -0.70
    StoreMessageInfo
    -0.65
     {?>
    -0.64
    uropa
    -0.58
    ldc
    -0.58
     "',
    -0.56
    Portale
    -0.54
    nitus
    -0.53
     continuant
    -0.52
    POSITIVE LOGITS
     allowable
    0.85
     max
    0.82
     Max
    0.79
     getMax
    0.77
     MAX
    0.77
     Verstappen
    0.69
     maks
    0.68
    setMax
    0.67
    Max
    0.66
    ALLOWED
    0.66
    Activations Density 0.082%

    No Known Activations