© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 31-GEMMASCOPE-RES-16K
    6. 13618
    Prev
    Next
    INDEX
    Explanations

    key moments in sports events, especially related to injuries and player performances

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

    sports statistics and numerical performance metrics in baseball and sports articles.

    oai_token-act-pair · claude-4-5-haikuTriggered by @emiglarou
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 31-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_31/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    UnusedPrivate
    -0.60
    transQ
    -0.60
     nahilalakip
    -0.59
     AssemblyCulture
    -0.55
    reamble
    -0.54
    ⓧ
    -0.53
    Portail
    -0.53
     CreateTagHelper
    -0.52
    WithIOException
    -0.52
     HasFactory
    -0.51
    POSITIVE LOGITS
     catch
    0.74
     Catch
    0.73
     catches
    0.67
     catching
    0.66
    Catch
    0.64
     CATCH
    0.61
     caught
    0.60
    CATCH
    0.60
     fielding
    0.59
    catch
    0.56
    Activations Density 0.068%

    No Known Activations