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. 12-GEMMASCOPE-RES-16K
    6. 14601
    Prev
    Next
    INDEX
    Explanations

    references to self-identity or personal existence

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Tiz
    -0.81
     Bue
    -0.78
     Lur
    -0.73
     Garrick
    -0.72
    ֵי
    -0.71
    tır
    -0.70
     Schen
    -0.70
     TRI
    -0.70
     deacon
    -0.69
     Pitman
    -0.69
    POSITIVE LOGITS
    selves
    1.54
    herself
    1.38
    Yourself
    1.37
    myself
    1.35
     herself
    1.33
     Yourself
    1.31
    Myself
    1.31
     himself
    1.31
     Himself
    1.31
     myself
    1.24
    Activations Density 0.046%

    No Known Activations