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

    Neuronpedia

    Jacobian LensNEW
    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. 4974
    Prev
    Next
    INDEX
    Explanations

    variations of concatenation or string formatting operations

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

    Code syntax or mathematical operators

    np_acts-logits-general · gemini-2.0-flash

    string concatenation

    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
     ?>>
    -0.66
    իս
    -0.57
    Бахар
    -0.56
    tagHelperRunner
    -0.55
    SetBool
    -0.55
     Ear
    -0.51
    bibinfo
    -0.51
    Ear
    -0.51
     ear
    -0.50
    úgó
    -0.50
    POSITIVE LOGITS
    ":"
    0.65
     '/'
    0.62
     "/"
    0.61
    "/"
    0.56
     ",
    0.54
    CPtr
    0.54
     "-"
    0.53
    ANDUM
    0.53
     '-'
    0.53
    ':'
    0.51
    Activations Density 0.033%

    No Known Activations