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
    4. Residual Stream - 16k
    5. 24-GEMMASCOPE-RES-16K
    6. 1175
    Prev
    Next
    INDEX
    Explanations

    code structure elements, specifically return statements and conditions

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

    Code snippets (e.g., Java, C++) with symbols

    np_acts-logits-general · gemini-2.0-flash

    statement terminators

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_24/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     estekak
    -1.00
     '\\;'
    -0.98
     autorytatywna
    -0.97
    ArrowToggle
    -0.91
    fjspx
    -0.90
    IsMutable
    -0.88
    <unused43>
    -0.87
    
    -0.87
    Хьажоргаш
    -0.86
     Wikimedijinoj
    -0.86
    POSITIVE LOGITS
    ↵↵
    0.56
    .
    0.44
    ↵
    0.43
    2
    0.41
    0
    0.40
    <eos>
    0.40
    ↵↵↵
    0.37
    1
    0.36
    }
    0.34
     }
    0.34
    Activations Density 0.163%

    No Known Activations