© 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. 5-GEMMASCOPE-RES-16K
    6. 3319
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "req."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.5.hook_resid_post
    Hook Layer
    5
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Coordenadas
    -0.67
     Rote
    -0.66
    دور
    -0.64
     Usher
    -0.60
    IMPORTED
    -0.58
    ום
    -0.58
    ابع
    -0.58
    rinth
    -0.57
    keyValue
    -0.57
    phur
    -0.57
    POSITIVE LOGITS
    req
    2.17
     req
    2.02
    REQ
    1.54
    Req
    1.51
     Req
    1.43
    reqs
    1.31
     REQ
    1.26
    ereq
    1.05
     المعيارى
    0.87
    Requis
    0.86
    Activations Density 0.036%

    No Known Activations