© 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-2-2B
    7. Residual Stream - 16k
    9. 4-GEMMASCOPE-RES-16K
    11. 15612
    Prev
    Next
    INDEX
    Explanations

    terms related to pharmacological and theoretical concepts in scientific contexts

    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
     houſe
    -0.84
     reaſon
    -0.83
     ſtate
    -0.83
     ſen
    -0.83
     eſſ
    -0.83
    rawDesc
    -0.82
     neceſſ
    -0.80
     quæ
    -0.79
     Efq
    -0.79
     ſta
    -0.79
    POSITIVE LOGITS
    ंदीखरीदारी
    0.44
     benne
    0.44
    ,
    0.44
     in
    0.42
    jā
    0.40
     below
    0.40
    Morrison
    0.40
     P
    0.40
     Did
    0.39
     without
    0.39
    Activations Density 0.608%

    No Known Activations