© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B-IT
    7. Residual Stream - 131k
    9. 9-GEMMASCOPE-RES-131K
    11. 19648
    Prev
    Next
    INDEX
    Explanations

    phrases indicating causation or the effects of certain actions or events

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

    preposition followed by noun phrase

    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
     sóc
    -0.39
    writeFieldEnd
    -0.35
    وانید
    -0.34
    AsUp
    -0.34
    Tikang
    -0.34
    vejec
    -0.33
    étit
    -0.32
    labus
    -0.32
    Scénario
    -0.32
    contentLoaded
    -0.32
    POSITIVE LOGITS
    OGND
    0.55
    })`
    0.54
    newArrayList
    0.54
    }();
    0.50
     kasarigan
    0.50
     AssemblyProduct
    0.49
    ManagedBean
    0.47
    GraphicsUnit
    0.46
    mberg
    0.46
     fVar
    0.45
    Activations Density 0.176%

    No Known Activations