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-2-2B
    4. Residual Stream - 16k
    5. 16-GEMMASCOPE-RES-16K
    6. 6044
    Prev
    Next
    INDEX
    Explanations

    code-related keywords, particularly those associated with libraries, modules, and functions in programming

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

    C/C++ header file guards

    np_acts-logits-general · gemini-2.0-flash

    `goog.`, `#ifndef`, `#define`

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ItemBackground
    -0.56
    SharedDtor
    -0.53
    ApiModelProperty
    -0.53
     JpaRepository
    -0.53
     culoare
    -0.52
    enity
    -0.51
    AttributeSet
    -0.48
     CallOverrides
    -0.47
     onAnimation
    -0.47
    CROSSTALK
    -0.46
    POSITIVE LOGITS
    SourceChecksum
    0.84
     ***!
    0.81
    moduleId
    0.73
    utnik
    0.71
    webpack
    0.70
     EconPapers
    0.65
    ValueStyle
    0.65
    /***/
    0.65
    __);
    0.64
     modules
    0.63
    Activations Density 0.033%

    No Known Activations