© 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-2-9B
    4. Residual Stream - 16k
    5. 14-GEMMASCOPE-RES-16K
    6. 8664
    Prev
    Next
    INDEX
    Explanations

    numerical representations of time and measurements related to performance records

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 14-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_14/width_16k/average_l0_67
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.14.hook_resid_post
    Hook Layer
    14
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ArrowToggle
    -0.69
    AsUp
    -0.65
     Савезне
    -0.60
    __':
    
    -0.57
    ArgsConstructor
    -0.56
    __":
    
    -0.55
    Personendaten
    -0.53
    XmlAccessorType
    -0.51
    rungsseite
    -0.50
     HasFactory
    -0.49
    POSITIVE LOGITS
     recorded
    0.46
     faster
    0.41
    vidéo
    0.40
    recorded
    0.39
     impressively
    0.39
    pantalón
    0.39
     impressive
    0.38
    faster
    0.38
     basah
    0.38
     fastest
    0.38
    Activations Density 0.036%

    No Known Activations