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. 91966
    Prev
    Next
    INDEX
    Explanations

    punctuation marks and special characters

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    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
     Correspond
    -0.41
     Initialized
    -0.40
     ACTUAL
    -0.37
    ActionListener
    -0.36
    onPressed
    -0.36
     Cotton
    -0.36
    sendRedirect
    -0.36
     SqlParameter
    -0.36
    onedDateTime
    -0.35
     HttpNotFound
    -0.35
    POSITIVE LOGITS
    SequentialGroup
    0.58
     Chwiliwch
    0.52
    RTDA
    0.50
     demografica
    0.50
     stream
    0.50
     ویکی‌پدی
    0.49
    stdc
    0.47
     STREAM
    0.47
    AndroidJUnit
    0.47
     pinulongan
    0.47
    Activations Density 0.000%

    No Known Activations