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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 22-GEMMASCOPE-RES-16K
    6. 13315
    Prev
    Next
    INDEX
    Explanations

    code structure elements related to data encoding and decoding processes

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

    Code-related terms and symbols

    np_acts-logits-general · gemini-2.0-flash

    objective-c method calls

    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
     V
    -0.91
     M
    -0.90
     A
    -0.89
     I
    -0.89
     L
    -0.87
     O
    -0.87
     N
    -0.86
     E
    -0.86
     van
    -0.86
    ,
    -0.85
    POSITIVE LOGITS
     itſelf
    1.76
     myſelf
    1.69
     pleaſure
    1.65
     Monfieur
    1.58
     poffible
    1.54
     purpoſe
    1.51
     raiſ
    1.50
     greateſt
    1.49
    tagHelperRunner
    1.45
     faſt
    1.43
    Activations Density 0.933%

    No Known Activations