© 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. 8-GEMMASCOPE-RES-16K
    6. 4876
    Prev
    Next
    INDEX
    Explanations

    coding constructs related to conditional statements and checks for null or empty values

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 8-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_8/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.hook_resid_post
    Hook Layer
    8
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ("")]
    
    -0.62
    Diwedd
    -0.58
     utterly
    -0.57
     faute
    -0.57
     wholly
    -0.54
     princes
    -0.52
     failure
    -0.51
     Failing
    -0.50
     dwar
    -0.50
    NullException
    -0.49
    POSITIVE LOGITS
    didSet
    0.92
    IsNotEmpty
    0.65
    isNotBlank
    0.61
    notEmpty
    0.60
     propTypes
    0.60
     الحره
    0.59
     typelib
    0.58
    NotEmpty
    0.58
     gefangen
    0.58
    Kesimpulan
    0.56
    Activations Density 0.124%

    No Known Activations