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. 7-GEMMASCOPE-RES-16K
    6. 6863
    Prev
    Next
    INDEX
    Explanations

    specific control flow structures and logical conditions in programming or scripting languages

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 7-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_7/width_16k/average_l0_69
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Hook Layer
    7
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    });
    
    -0.52
    ".
    
    -0.51
     '').
    -0.51
     }}"></
    -0.51
     Corm
    -0.50
    URIComponent
    -0.50
    ղ
    -0.50
    "/>
    
    -0.48
    kháu
    -0.48
     elő
    -0.47
    POSITIVE LOGITS
    SBATCH
    0.72
     ostavi
    0.68
     élevées
    0.67
     ProtoMessage
    0.65
     CommonModule
    0.63
    帖最后由
    0.63
     significativos
    0.61
     propOrder
    0.60
     DbSet
    0.60
     ComVisible
    0.59
    Activations Density 0.246%

    No Known Activations