Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 51023
    Prev
    Next
    INDEX
    Explanations

    terms related to lattice structures and percolation thresholds in mathematical contexts

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

    checkerboard lattice

    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
     '\\;'
    -0.72
    ValueStyle
    -0.54
     صوتيه
    -0.50
     Roskov
    -0.50
     Waray
    -0.49
    THY
    -0.47
    ScopeManager
    -0.45
    TokenNameRPAREN
    -0.44
    WaitGroup
    -0.43
    Autoritní
    -0.42
    POSITIVE LOGITS
    PutPixel
    0.62
    fromnode
    0.45
    setupUi
    0.43
     Fant
    0.37
    brainly
    0.33
    QUADS
    0.32
     Receiving
    0.32
    Receiving
    0.31
     BoxFit
    0.31
    ÂN
    0.30
    Activations Density 0.232%

    No Known Activations