© 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-2-9B-IT
    4. Residual Stream - 131k
    5. 9-GEMMASCOPE-RES-131K
    6. 85142
    Prev
    Next
    INDEX
    Explanations

    mentions of user interface components and elements related to graphical programming

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

    Toxoplasma, traceback, UIImageView

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_131k/average_l0_121
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     abz
    -0.38
    KommentareTeilen
    -0.37
    rungsseite
    -0.36
    EnableWeb
    -0.33
    mtext
    -0.33
     isof
    -0.33
     }{@
    -0.32
    ghis
    -0.31
    /*-
    -0.31
     tė
    -0.31
    POSITIVE LOGITS
    TouchableOpacity
    2.70
     Touchable
    1.53
    Touchable
    0.84
     UIImageView
    0.71
    disposing
    0.67
     traceback
    0.65
     &___
    0.64
    uxxxx
    0.63
    AsUp
    0.63
     ProtoMessage
    0.61
    Activations Density 0.001%

    No Known Activations