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-2-9B
    4. Residual Stream - 16k
    5. 36-GEMMASCOPE-RES-16K
    6. 14612
    Prev
    Next
    INDEX
    Explanations

    references to aviation, particularly in the context of airport operations and developments

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 36-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_36/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.36.hook_resid_post
    Hook Layer
    36
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ParallelGroup
    -0.38
     suspiciously
    -0.38
     surprisingly
    -0.37
     stupidly
    -0.36
    oredCriteria
    -0.35
     sneaky
    -0.34
     mistakenly
    -0.34
     ridiculously
    -0.33
    prisingly
    -0.33
    prefixes
    -0.32
    POSITIVE LOGITS
    :✨
    0.62
     conducive
    0.57
    Toponymie
    0.54
    Tikang
    0.54
     Chwiliwch
    0.53
    تقاوى
    0.53
    ModelSerializer
    0.53
     socio
    0.52
    Diweddarwch
    0.50
    лтамалар
    0.50
    Activations Density 0.060%

    No Known Activations