© 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. 22-GEMMASCOPE-RES-16K
    11. 4039
    Prev
    Next
    INDEX
    Explanations

    keywords and function calls related to object-oriented programming in a coding context

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

    Code snippets and mathematical notation

    np_acts-logits-general · gemini-2.0-flash

    code or specific sequences

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    .
    -0.69
    StoryboardSegue
    -0.64
    Personendaten
    -0.57
    phus
    -0.53
     she
    -0.51
    TagMode
    -0.49
    LookAnd
    -0.48
    crollView
    -0.46
    ',{
    -0.46
    rawdę
    -0.46
    POSITIVE LOGITS
    ->
    1.80
    ()->
    1.38
    ]->
    1.26
    ")->
    1.25
    )->
    1.19
    _->
    1.15
    ']->
    1.14
     ->
    1.07
    ')->
    1.01
    ->$
    0.95
    Activations Density 0.189%

    No Known Activations