© 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. 0-GEMMASCOPE-RES-16K
    6. 8227
    Prev
    Next
    INDEX
    Explanations

    terms related to the process of registration and recording

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 0-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_0/width_16k/average_l0_105
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.hook_resid_post
    Hook Layer
    0
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     démocr
    -0.59
     aéro
    -0.57
    entrevista
    -0.57
     GoogleFonts
    -0.56
    muerzo
    -0.56
     للمعارف
    -0.55
    ыгана
    -0.55
     déput
    -0.55
     sauvage
    -0.54
     cucchiai
    -0.54
    POSITIVE LOGITS
     regist
    2.48
     Regist
    2.28
     record
    2.21
    regist
    2.18
     records
    2.14
     Record
    2.13
     registro
    2.07
    Regist
    2.06
     RECORD
    2.06
    record
    2.05
    Activations Density 0.063%

    No Known Activations