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. 8-GEMMASCOPE-RES-16K
    6. 4879
    Prev
    Next
    INDEX
    Explanations

    references to the concept of fighting or struggle, often in the context of overcoming adversity or achieving goals

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 8-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_8/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.hook_resid_post
    Hook Layer
    8
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     dAtA
    -0.74
     généraux
    -0.68
     placés
    -0.68
     Boon
    -0.67
    Ils
    -0.67
    nextElement
    -0.67
     conséquence
    -0.67
    berapa
    -0.66
     jeunesse
    -0.65
    avra
    -0.65
    POSITIVE LOGITS
    fight
    1.92
     fight
    1.90
     fought
    1.76
     fights
    1.76
     FIGHT
    1.70
     Fight
    1.70
     fighting
    1.64
     Fighting
    1.63
    fights
    1.59
    fighting
    1.58
    Activations Density 0.066%

    No Known Activations