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-2-2B
    4. Residual Stream - 16k
    5. 7-GEMMASCOPE-RES-16K
    6. 8943
    Prev
    Next
    INDEX
    Explanations

    concepts related to personality and personal traits

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 7-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_7/width_16k/average_l0_69
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Hook Layer
    7
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    CrossRef
    -0.79
    er
    -0.74
    ArgsConstructor
    -0.74
     borer
    -0.74
     '\\;'
    -0.74
     flecha
    -0.73
     Meksiku
    -0.72
     Anya
    -0.71
    MigrationBuilder
    -0.70
     icona
    -0.70
    POSITIVE LOGITS
     personality
    1.17
     Personality
    1.11
     Soul
    1.05
    Personality
    1.01
     SOUL
    1.00
     personalities
    0.99
     soul
    0.97
    personality
    0.95
     Souls
    0.94
    Soul
    0.90
    Activations Density 0.084%

    No Known Activations