© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 22-GEMMASCOPE-RES-16K
    11. 10591
    Prev
    Next
    INDEX
    Explanations

    structured definitions and technical specifications

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

    Bitwise operations and masking

    np_acts-logits-general · gemini-2.0-flash

    bitwise operations on masks and flags

    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
     WaitForSeconds
    -0.55
    CppMethod
    -0.48
     namanya
    -0.45
    stanz
    -0.43
     sto
    -0.42
    chov
    -0.42
    escens
    -0.42
     gian
    -0.41
    +"/
    -0.41
    nani
    -0.41
    POSITIVE LOGITS
     bit
    1.41
    bit
    1.28
     bits
    1.26
     mask
    1.24
     Bit
    1.20
    Bit
    1.20
     Bits
    1.18
    bits
    1.16
    mask
    1.16
     Mask
    1.13
    Activations Density 0.874%

    No Known Activations