© 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-IT
    4. Residual Stream - 16k
    5. 9-GEMMASCOPE-RES-16K
    6. 10802
    Prev
    Next
    INDEX
    Explanations

    references to air and its various characteristics and roles in different contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    "air" or "air conditioning"

    np_acts-logits-general · gemini-2.0-flash

    air conditioning, air purifier

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    rawDesc
    -0.47
    ുന്ന
    -0.45
    onom
    -0.42
    onts
    -0.40
    ugat
    -0.40
     McGu
    -0.40
    itere
    -0.39
    atelle
    -0.38
    assero
    -0.37
    onacci
    -0.37
    POSITIVE LOGITS
     air
    2.41
    Air
    2.25
     Air
    2.22
     AIR
    2.08
    air
    1.98
    AIR
    1.84
     Luft
    1.48
     aire
    1.45
     airs
    1.43
     luft
    1.43
    Activations Density 0.092%

    No Known Activations