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. 6-GEMMASCOPE-RES-16K
    6. 12116
    Prev
    Next
    INDEX
    Explanations

    patterns of indentation in code or structured text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 6-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_6/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.6.hook_resid_post
    Hook Layer
    6
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    AsUp
    -0.55
    clonal
    -0.55
     Réponses
    -0.55
     repress
    -0.53
    salms
    -0.53
     tslint
    -0.51
    itness
    -0.50
    шру
    -0.49
    !*\
    -0.49
    akuan
    -0.48
    POSITIVE LOGITS
    rungsseite
    0.87
    Hozzáférés
    0.87
    تقاوى
    0.81
    __':
    
    0.79
    adaptiveStyles
    0.79
    dafx
    0.72
    }*/
    
    0.69
     autorytatywna
    0.68
     насељу
    0.66
    __":
    
    0.66
    Activations Density 0.049%

    No Known Activations