© 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-2-9B
    7. Residual Stream - 16k
    9. 31-GEMMASCOPE-RES-16K
    11. 620
    Prev
    Next
    INDEX
    Explanations

    references to individual experiences and perspectives

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

    first-person pronouns and contractions ("you", "I'm", "you're").

    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
     an
    -0.31
     a
    -0.31
     abgesch
    -0.31
    '}),
    -0.30
     either
    -0.29
     Haven
    -0.29
     inkl
    -0.29
    only
    -0.27
    ching
    -0.27
     incl
    -0.27
    POSITIVE LOGITS
    AndEndTag
    0.85
    transQ
    0.77
    ſammen
    0.74
    styleType
    0.73
     مرئيه
    0.71
     مشين
    0.67
    RegressionTest
    0.66
     createSlice
    0.66
    expandindo
    0.66
    enterOuterAlt
    0.65
    Activations Density 0.402%

    No Known Activations