© 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. 10208
    Prev
    Next
    INDEX
    Explanations

    specific programming-related terms and references associated with file operations and functions

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

    IBM-related software or systems

    np_acts-logits-general · gemini-2.0-flash

    IBM SAS software

    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
     ujednoznacz
    -0.64
    ksikon
    -0.52
     Wayback
    -0.52
    Brainz
    -0.52
    arithmic
    -0.51
     mapStateToProps
    -0.51
    cshtml
    -0.51
    Ufficio
    -0.50
    shame
    -0.49
     réguli
    -0.48
    POSITIVE LOGITS
     abends
    0.70
     IBM
    0.68
     abend
    0.66
     tape
    0.64
     Abend
    0.63
     متعلقه
    0.62
    IBM
    0.62
    tape
    0.60
    AccessorTable
    0.59
     tapes
    0.58
    Activations Density 0.270%

    No Known Activations