© 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. 13219
    Prev
    Next
    INDEX
    Explanations

    technical terms and definitions related to processes and calculations

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

    Mathematical or logical expressions

    np_acts-logits-general · gemini-2.0-flash

    code definitions and logical operators

    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
     Meksiku
    -0.80
     ProtoMessage
    -0.74
    M
    -0.73
    +#+#
    -0.72
    methyl
    -0.71
    margin
    -0.70
    Modified
    -0.70
     margin
    -0.69
     million
    -0.69
     memorandum
    -0.68
    POSITIVE LOGITS
    ########.
    0.55
     Efq
    0.49
     itſelf
    0.43
     faſt
    0.42
     Reſ
    0.41
     leſs
    0.41
     Anſ
    0.40
    delige
    0.40
    ſelves
    0.40
    pirable
    0.39
    Activations Density 0.826%

    No Known Activations