Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 7-GEMMASCOPE-RES-16K
    6. 7252
    Prev
    Next
    INDEX
    Explanations

    references to beginnings or openings of events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 7-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_7/width_16k/average_l0_69
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Hook Layer
    7
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    enumerate
    -0.79
    er
    -0.77
    itemize
    -0.63
     искать
    -0.61
    jö
    -0.59
     ríos
    -0.58
     вопросам
    -0.58
    quot
    -0.57
    ⿴
    -0.57
    aronder
    -0.57
    POSITIVE LOGITS
    beginning
    1.19
     commencement
    1.18
     opening
    1.18
    Opening
    1.17
     OPENING
    1.15
    opening
    1.14
     Opening
    1.14
     beginnings
    1.13
     beginning
    1.12
     début
    1.09
    Activations Density 0.142%

    No Known Activations