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. 9370
    Prev
    Next
    INDEX
    Explanations

    references to heroes and heroism in various contexts

    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
    bibinfo
    -0.76
     Nü
    -0.72
    исленность
    -0.71
     Cym
    -0.69
    Richie
    -0.68
     Estat
    -0.68
    Richards
    -0.68
     Kep
    -0.68
     Grimes
    -0.67
     devenue
    -0.67
    POSITIVE LOGITS
     Hero
    1.22
    Hero
    1.19
    HERO
    1.09
    hero
    1.09
     HERO
    1.08
     SAL
    1.08
    salary
    1.03
     sal
    1.03
     Sal
    1.02
     salon
    1.01
    Activations Density 0.047%

    No Known Activations