© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 1-GEMMASCOPE-RES-16K
    6. 9876
    Prev
    Next
    INDEX
    Explanations

    references to sauces

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 1-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_1/width_16k/average_l0_102
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.1.hook_resid_post
    Hook Layer
    1
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Viited
    -0.67
    ————————————————
    -0.62
     antaranya
    -0.60
     spesies
    -0.60
    jface
    -0.55
    Expire
    -0.54
    complexContent
    -0.53
    🏾
    -0.51
    ConstraintMaker
    -0.51
    ună
    -0.50
    POSITIVE LOGITS
     sauce
    0.68
     forgive
    0.68
    ]='\
    0.66
    sauce
    0.63
    }],
    
    0.63
    Promise
    0.62
    OGND
    0.61
    )}</
    0.60
     emplois
    0.60
    VersionUID
    0.60
    Activations Density 0.096%

    No Known Activations