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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 11-GEMMASCOPE-RES-16K
    6. 13148
    Prev
    Next
    INDEX
    Explanations

    API request methods and their parameters in code

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 11-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_11/width_16k/average_l0_80
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Hook Layer
    11
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    anthe
    -0.53
     NRC
    -0.52
     padx
    -0.51
     cellpadding
    -0.50
    ეს
    -0.49
     foramen
    -0.47
     cellspacing
    -0.47
     Prov
    -0.47
     arbitration
    -0.47
     Contra
    -0.46
    POSITIVE LOGITS
    ConstraintMaker
    0.76
    WithIOException
    0.72
     للمعارف
    0.61
    Tē
    0.57
     autorytatywna
    0.57
     саны
    0.55
    ⓧ
    0.55
     kaynağından
    0.54
    LookAnd
    0.54
    yargs
    0.54
    Activations Density 0.156%

    No Known Activations