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-2-2B
    4. Residual Stream - 16k
    5. 24-GEMMASCOPE-RES-16K
    6. 8296
    Prev
    Next
    INDEX
    Explanations

    code-related terms and constructs in programming syntax

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

    C struct definitions

    np_acts-logits-general · gemini-2.0-flash

    network packet structures

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 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
    ூர்
    -0.48
     Grosvenor
    -0.45
     umożliwia
    -0.44
     }}">
    -0.43
     Employ
    -0.42
    nemonic
    -0.41
    pesar
    -0.41
     Portion
    -0.40
     réput
    -0.40
     ensues
    -0.40
    POSITIVE LOGITS
     beginnetje
    0.78
    __':
    
    0.78
    Portail
    0.77
     الحره
    0.73
    	
    0.72
    JsonHelper
    0.67
    enumii
    0.63
    }
    0.62
     للاسماء
    0.61
    солю
    0.60
    Activations Density 0.050%

    No Known Activations