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. 1242
    Prev
    Next
    INDEX
    Explanations

    instances and variations of the word "fluent" and related terms

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

    fluent or fluently

    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
     OSError
    -0.51
    fbox
    -0.43
     box
    -0.39
     Inscrivez
    -0.38
     fotográfico
    -0.37
     useAppContext
    -0.37
     mortes
    -0.36
    DatabaseError
    -0.36
     Comstock
    -0.36
     balls
    -0.35
    POSITIVE LOGITS
     Fluent
    2.98
    Fluent
    2.59
     fluent
    2.20
    fluent
    2.17
     fluency
    1.47
     FLU
    1.17
    FLU
    1.01
    Flu
    0.96
     Flu
    0.94
     fluence
    0.89
    Activations Density 0.001%

    No Known Activations