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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 15-GEMMASCOPE-RES-16K
    11. 4525
    Prev
    Next
    INDEX
    Explanations

    complex relationships and comparisons between different entities or concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_15/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     DMV
    -0.49
     }}"
    -0.43
     }}{\
    -0.43
     Courant
    -0.42
     }}</
    -0.42
    tagHelperRunner
    -0.42
    例文
    -0.42
     Uz
    -0.41
    脱
    -0.41
    }}
    -0.40
    POSITIVE LOGITS
    AsUp
    0.84
    RuleContext
    0.71
     تضيفلها
    0.70
     تانيه
    0.66
    +#+
    0.65
    ătate
    0.64
    BackStack
    0.63
     voire
    0.62
     contextLoads
    0.62
    GeoNames
    0.61
    Activations Density 0.637%

    No Known Activations