Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 75018
    Prev
    Next
    INDEX
    Explanations

    references to the name "Eric."

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

    people named Eric

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    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
    --}}
    -0.45
    .~\
    -0.44
    )"),
    -0.43
    ,_
    -0.43
    रीदारी
    -0.42
    }},\
    -0.42
    ]='\
    -0.42
     &_
    -0.42
    );\
    -0.42
     --}}
    -0.41
    POSITIVE LOGITS
     Eric
    0.90
     Erick
    0.84
     ERIC
    0.83
    Erick
    0.82
    Eric
    0.80
     Ericsson
    0.78
    ERIC
    0.71
    eric
    0.66
     Eriksson
    0.65
     Erik
    0.64
    Activations Density 0.005%

    No Known Activations