© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    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. 16197
    Prev
    Next
    INDEX
    Explanations

    programming constructs related to data structures and function definitions

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

    Code snippets/data structures in code

    np_acts-logits-general · gemini-2.0-flash

    code termination markers

    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
    .")
    
    -2.13
    "):
    
    -2.06
    !")
    
    -2.02
    '):
    
    -2.00
    "]);
    
    -1.95
    '));
    
    -1.93
    '),
    
    -1.92
    "));
    
    -1.92
    "),
    
    -1.91
    '],
    
    -1.90
    POSITIVE LOGITS
    ।
    0.47
     awakeFromNib
    0.45
    omia
    0.43
     Trouver
    0.43
    acon
    0.42
    योग
    0.42
     pleins
    0.42
    peque
    0.41
    </tr>
    0.41
     bord
    0.41
    Activations Density 0.526%

    No Known Activations