© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 18-GEMMASCOPE-RES-16K
    11. 12460
    Prev
    Next
    INDEX
    Explanations

    references to social media interactions and user details

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Tokens after "follow" or "followers"

    np_acts-logits-general · gemini-2.0-flash

    following

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    IVEREF
    -0.56
    invokeLater
    -0.51
    éz
    -0.49
     compound
    -0.47
    äsident
    -0.47
    евна
    -0.47
     Compound
    -0.46
    Опис
    -0.46
    casse
    -0.45
    LoggerFactory
    -0.45
    POSITIVE LOGITS
     follow
    1.78
    follow
    1.78
     Follow
    1.72
    Follow
    1.70
     FOLLOW
    1.66
     follows
    1.62
    FOLLOW
    1.51
     followers
    1.47
     Follows
    1.46
     follower
    1.44
    Activations Density 0.138%

    No Known Activations