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. 1067
    Prev
    Next
    INDEX
    Explanations

    punctuation marks, particularly periods, slashes, and other special characters

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

    nationalities or places of origin

    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
    WaitGroup
    -0.74
     صوتيه
    -0.71
    setViewportView
    -0.65
    AddTagHelper
    -0.65
    ◚
    -0.64
     препратки
    -0.63
    InputTagHelper
    -0.62
     برانيه
    -0.62
     marti
    -0.61
     jScrollPane
    -0.60
    POSITIVE LOGITS
    <bos>
    0.44
     Indian
    0.40
     Italian
    0.38
     huiles
    0.36
     Brazilian
    0.36
     Brasileira
    0.36
     British
    0.36
     Grecs
    0.35
     Canadian
    0.34
     brasileiros
    0.33
    Activations Density 0.001%

    No Known Activations