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. 98021
    Prev
    Next
    INDEX
    Explanations

    expressions and terms related to identity and existence

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

    anybody, anyone, nobody, someone, soul

    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
     Федерации
    -0.33
     angep
    -0.31
    数
    -0.30
    ใช่
    -0.30
    巧
    -0.30
     del
    -0.30
    送
    -0.29
     enlever
    -0.29
    ớp
    -0.28
    asthan
    -0.28
    POSITIVE LOGITS
     anybody
    1.00
    anyone
    0.99
     anyone
    0.98
    everyone
    0.96
    everybody
    0.96
     everyone
    0.94
     everybody
    0.92
     ANYONE
    0.87
     nobody
    0.84
    someone
    0.84
    Activations Density 0.117%

    No Known Activations