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. 7008
    Prev
    Next
    INDEX
    Explanations

    math expressions and their related formatting

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

    \protect\independenT{\perp}

    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
     fubject
    -0.59
     ſtate
    -0.52
     Stirn
    -0.51
     huel
    -0.50
     houſe
    -0.50
     occaf
    -0.49
     purpoſe
    -0.49
     lineup
    -0.48
     itſelf
    -0.48
    )})
    -0.48
    POSITIVE LOGITS
    {\
    1.81
     {\
    1.39
    ]{\
    1.11
    ){\
    1.02
    {{\
    0.97
     ${\
    0.94
    ({\
    0.94
    ={\
    0.91
    }{\
    0.91
    ,{\
    0.91
    Activations Density 0.188%

    No Known Activations