© 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-2-9B-IT
    7. Residual Stream - 131k
    9. 20-GEMMASCOPE-RES-131K
    11. 43309
    Prev
    Next
    INDEX
    Explanations

    specific formatting or structuring elements in text, particularly related to data or coding contexts

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

    mathematical or code ranges

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    LookAnd
    -0.68
    fromnode
    -0.68
    tagHelperRunner
    -0.64
     Administrativna
    -0.59
    uxxxx
    -0.59
    GEBURTSDATUM
    -0.55
    ſt
    -0.55
    Примечания
    -0.55
    RTLR
    -0.54
    AndEndTag
    -0.54
    POSITIVE LOGITS
    MessageTagHelper
    0.31
    })*/
    0.29
     Савезне
    0.28
    ഞ്
    0.25
     Cause
    0.25
     '\\;'
    0.25
     «
    0.24
    tikzpicture
    0.24
     iprot
    0.24
    「
    0.24
    Activations Density 0.024%

    No Known Activations