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. 21-GEMMASCOPE-RES-16K
    6. 6633
    Prev
    Next
    INDEX
    Explanations

    functions and methods related to file handling and serialization in programming contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 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
     hashCode
    -0.52
    ptor
    -0.45
     motto
    -0.45
     supports
    -0.44
     int
    -0.43
     ter
    -0.42
     I
    -0.42
    statusCode
    -0.42
     size
    -0.42
    .
    -0.41
    POSITIVE LOGITS
    create
    0.91
     onCreateView
    0.88
     Create
    0.88
    Create
    0.87
     create
    0.84
     createSlice
    0.78
    createComponent
    0.78
     Instantiate
    0.78
     Creates
    0.77
     חיצוניים
    0.76
    Activations Density 0.132%

    No Known Activations