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-IT
    4. Residual Stream - 131k
    5. 9-GEMMASCOPE-RES-131K
    6. 124022
    Prev
    Next
    INDEX
    Explanations

    mentions and references to ethanol in various contexts

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

    ethanol and alcohol precipitation

    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-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_131k/average_l0_121
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    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
     للمعارف
    -0.54
    balleur
    -0.50
     AssemblyCulture
    -0.49
     يتيمه
    -0.47
    oa̍t
    -0.47
    nezeu
    -0.46
    ########.
    -0.45
    StructEnd
    -0.42
     województwie
    -0.42
     Dumnezeu
    -0.41
    POSITIVE LOGITS
     Alcohol
    0.64
    alcohol
    0.60
     alcohol
    0.60
    Alcohol
    0.60
     acetone
    0.59
    llac
    0.54
     Alkohol
    0.53
    酒精
    0.49
    alcool
    0.47
     alcohols
    0.47
    Activations Density 0.152%

    No Known Activations