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-2-9B
    4. Residual Stream - 16k
    5. 28-GEMMASCOPE-RES-16K
    6. 4143
    Prev
    Next
    INDEX
    Explanations

    segments of code that define data structures or parameters

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Code, especially system calls and constants

    np_acts-logits-general · gemini-2.0-flash

    autorest

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 28-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_28/width_16k/average_l0_119
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.28.hook_resid_post
    Hook Layer
    28
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     San
    -0.32
     Ayrıca
    -0.31
     ring
    -0.30
    ')));
    -0.30
     or
    -0.29
     Pfe
    -0.28
     into
    -0.28
    mtrl
    -0.28
     par
    -0.27
     Wartung
    -0.27
    POSITIVE LOGITS
     otomatig
    0.94
    protoimpl
    0.93
    +#+
    0.93
    ########.
    0.89
     Paglinawan
    0.81
     للمعارف
    0.79
     للاسماء
    0.75
     autorytatywna
    0.74
     يتيمه
    0.74
     lenker
    0.73
    Activations Density 0.528%

    No Known Activations