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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 21-GEMMASCOPE-RES-16K
    6. 6133
    Prev
    Next
    INDEX
    Explanations

    C++ programming constructs and type definitions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_21/width_16k/average_l0_129
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    +#+#
    -0.65
    Chham
    -0.61
    ScopeManager
    -0.61
    TagHelper
    -0.59
    сылкі
    -0.57
     myſelf
    -0.57
     للمعارف
    -0.57
     المعيارى
    -0.55
    EndInit
    -0.55
    ępnie
    -0.54
    POSITIVE LOGITS
    ifdef
    0.53
    define
    0.50
    VersionUID
    0.38
     define
    0.37
     Package
    0.35
     Automotive
    0.35
    assert
    0.33
    cplusplus
    0.32
     defined
    0.31
     Version
    0.31
    Activations Density 0.733%

    No Known Activations