© 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. 2953
    Prev
    Next
    INDEX
    Explanations

    elements related to database schemas and queries

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

    Code, expressions, or programming-related text

    np_acts-logits-general · gemini-2.0-flash

    apache and programming code

    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
     foundations
    -0.69
     basis
    -0.67
     foundation
    -0.66
     Basis
    -0.56
    foundation
    -0.54
    Foundation
    -0.53
     Foundations
    -0.53
     Foundation
    -0.51
     fundamento
    -0.49
     основу
    -0.49
    POSITIVE LOGITS
     itſelf
    0.83
    oa̍t
    0.80
    Rujuakan
    0.79
     myſelf
    0.77
    ProcessEvent
    0.75
    TagMode
    0.75
     '\\;'
    0.74
    :✨
    0.74
     pleaſure
    0.74
    MLLoader
    0.73
    Activations Density 0.153%

    No Known Activations