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. 102822
    Prev
    Next
    INDEX
    Explanations

    conjunctions that indicate additional components or quantities

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

    plus followed by numbers or nouns

    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
    UserScript
    -0.48
     volant
    -0.46
    ScopeManager
    -0.45
     Houſe
    -0.44
    ArgumentParser
    -0.43
     airfoil
    -0.42
     houſe
    -0.42
    WriteBarrier
    -0.41
     VIAF
    -0.41
     ModelRenderer
    -0.40
    POSITIVE LOGITS
     plus
    1.31
     плюс
    1.03
    plus
    0.93
     ditambah
    0.82
     PLUS
    0.71
    +
    0.68
     nebst
    0.68
     minus
    0.67
    再加上
    0.67
     $+
    0.65
    Activations Density 0.009%

    No Known Activations