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. 12-GEMMASCOPE-RES-16K
    6. 9872
    Prev
    Next
    INDEX
    Explanations

    elements of programming code, specifically related to file handling and memory management

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    java
    -0.46
    ami
    -0.42
    امی
    -0.41
    lei
    -0.40
    VersionUID
    -0.39
    
    -0.39
     manqué
    -0.39
    ťaž
    -0.39
    とも
    -0.38
     Schnitt
    -0.38
    POSITIVE LOGITS
    ########.
    1.73
    :+:
    1.24
    #+#
    1.17
    libft
    1.08
    EndProject
    0.91
    ftagPool
    0.84
     للاسماء
    0.75
    SourceChecksum
    0.73
    MigrationBuilder
    0.73
    ⓧ
    0.72
    Activations Density 0.203%

    No Known Activations