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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 6264
    Prev
    Next
    INDEX
    Explanations

    elements related to data parsing and processing in code

    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
    sidemargin
    -0.58
    GraphicsUnit
    -0.57
     Lightboxes
    -0.57
    getColumnIndex
    -0.56
     Paglinawan
    -0.55
    fillType
    -0.55
    ErrorListener
    -0.54
    twimg
    -0.54
     fanns
    -0.53
    DebuggerNonUser
    -0.53
    POSITIVE LOGITS
     contents
    1.23
     string
    1.14
     content
    1.14
    string
    1.02
    content
    1.02
    contents
    1.00
    Contents
    0.97
     Contents
    0.97
     strings
    0.95
     text
    0.93
    Activations Density 0.729%

    No Known Activations