© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 24-GEMMASCOPE-RES-16K
    11. 14651
    Prev
    Next
    INDEX
    Explanations

    references to academic authorship and editorial processes

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

    edits or editing

    np_acts-logits-general · gemini-2.0-flash

    editing and revising

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    enterOuterAlt
    -0.65
    setVerticalGroup
    -0.58
     registre
    -0.51
    forName
    -0.49
     ClassNotFound
    -0.49
    PullParser
    -0.49
    audiovisuel
    -0.48
    forRoot
    -0.48
     pursu
    -0.47
    ContextHolder
    -0.47
    POSITIVE LOGITS
     edit
    3.40
     editing
    3.17
     Edit
    2.99
     edits
    2.95
    edit
    2.91
     Editing
    2.80
     edited
    2.79
    Edit
    2.77
     editor
    2.75
     editors
    2.69
    Activations Density 0.289%

    No Known Activations