© 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 - 131k
    5. 9-GEMMASCOPE-RES-131K
    6. 4974
    Prev
    Next
    INDEX
    Explanations

    references to minimum and maximum values, particularly in relation to parameters or settings

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

    maximum value or limit

    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
    Sci
    -0.62
     Sci
    -0.52
    sci
    -0.50
    flip
    -0.49
    Dri
    -0.48
    len
    -0.48
    Brit
    -0.47
     critters
    -0.47
    list
    -0.45
    blij
    -0.45
    POSITIVE LOGITS
     maximum
    1.79
    maximum
    1.76
    Maximum
    1.75
     Maximum
    1.73
     MAXIMUM
    1.48
    MAXIMUM
    1.42
    setMaximum
    1.21
     maksimum
    1.15
     maxima
    1.06
     maxim
    1.05
    Activations Density 0.013%

    No Known Activations