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. 23-GEMMASCOPE-RES-16K
    6. 12049
    Prev
    Next
    INDEX
    Explanations

    terms related to file validation and acceptable extensions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 23-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_23/width_16k/average_l0_75
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.hook_resid_post
    Hook Layer
    23
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     հղումներ
    -0.67
    SourceChecksum
    -0.61
    GEBURTSDATUM
    -0.53
    UpInside
    -0.52
    IndentedString
    -0.51
    AddTagHelper
    -0.50
     Schein
    -0.49
    windowFixed
    -0.48
    AntiForgeryToken
    -0.48
    Revenir
    -0.46
    POSITIVE LOGITS
     extension
    4.05
     Extension
    3.64
     extensions
    3.54
    extension
    3.50
    Extension
    3.37
     extend
    3.27
     EXTENSION
    3.20
     extending
    3.13
     Extensions
    3.13
     extended
    3.12
    Activations Density 0.500%

    No Known Activations