© 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. 4-GEMMASCOPE-RES-16K
    6. 953
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions and operations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 4-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_4/width_16k/average_l0_124
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.hook_resid_post
    Hook Layer
    4
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    pendicular
    -0.64
     Schuh
    -0.64
     Mazz
    -0.63
    mybatisplus
    -0.62
    THREE
    -0.62
     vän
    -0.62
     kommet
    -0.61
     Steff
    -0.61
    CopyWith
    -0.61
    GLOBALS
    -0.61
    POSITIVE LOGITS
     slan
    0.74
     Barbier
    0.67
    CDCl
    0.63
     amo
    0.63
     Altos
    0.62
     Rye
    0.61
     CURIAM
    0.61
     Dage
    0.60
    ¨
    0.60
    PreferredItem
    0.59
    Activations Density 0.793%

    No Known Activations