© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 37-GEMMASCOPE-RES-16K
    11. 4098
    Prev
    Next
    INDEX
    Explanations

    references to characters and their relationships

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 37-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_37/width_16k/average_l0_124
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.37.hook_resid_post
    Hook Layer
    37
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ❹
    -0.48
     चीज़ों
    -0.48
     myſelf
    -0.48
    majority
    -0.47
    styleType
    -0.47
    ValueStyle
    -0.44
     zdar
    -0.44
    ]")]
    -0.43
    ]),
    -0.42
    Majority
    -0.42
    POSITIVE LOGITS
     mom
    0.89
     dad
    0.86
     boyfriend
    0.80
     parents
    0.80
     grandmother
    0.77
     moms
    0.76
     girlfriend
    0.73
     grandma
    0.73
     mommy
    0.71
     virginity
    0.71
    Activations Density 0.382%

    No Known Activations