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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 22-GEMMASCOPE-RES-16K
    6. 10384
    Prev
    Next
    INDEX
    Explanations

    parameters and properties related to layout design in code

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

    Followed by ":" or "="

    np_acts-logits-general · gemini-2.0-flash

    programming property assignment

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    исленность
    -0.76
    ":["
    -0.57
    =["
    -0.52
    (@"%@",
    -0.52
    (&
    -0.52
    ]["
    -0.52
    (&_
    -0.51
    (['/
    -0.50
    ateria
    -0.50
    :['
    -0.48
    POSITIVE LOGITS
    DockStyle
    0.86
     يتيمه
    0.83
    VersionUID
    0.74
     мәкал
    0.71
     CreateTagHelper
    0.69
    NUMX
    0.63
    HasForeignKey
    0.62
     wynosi
    0.62
    vably
    0.61
    ChildScrollView
    0.60
    Activations Density 0.229%

    No Known Activations