© 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. 4963
    Prev
    Next
    INDEX
    Explanations

    content related to social media and self-presentation

    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
     Majefty
    -0.47
     pleaſure
    -0.47
     AllAfrica
    -0.45
     rootReducer
    -0.44
    ſelves
    -0.44
    umque
    -0.44
    lwjgl
    -0.43
     neceff
    -0.42
     fhew
    -0.42
     poffible
    -0.42
    POSITIVE LOGITS
     IG
    1.07
     Instagram
    1.07
     Reels
    1.02
     Stories
    0.96
    Instagram
    0.93
    Stories
    0.87
     reels
    0.87
     Insta
    0.84
     followers
    0.83
     posts
    0.80
    Activations Density 0.075%

    No Known Activations