Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 10747
    Prev
    Next
    INDEX
    Explanations

    proper nouns, particularly names and geographical locations

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

    Indian names and locations

    np_acts-logits-general · gemini-2.0-flash

    Indian surnames and locations

    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
     unknownFields
    -0.45
    ValueStyle
    -0.45
     californ
    -0.44
    expandindo
    -0.42
     OkHttpClient
    -0.40
    SourceChecksum
    -0.37
     nahilalakip
    -0.36
     SwitchCompat
    -0.36
    crollView
    -0.36
    Rptr
    -0.36
    POSITIVE LOGITS
     Kolkata
    0.77
    cutta
    0.74
     Bengali
    0.70
     Bengal
    0.70
     Calcutta
    0.69
    Kolkata
    0.69
    olkata
    0.65
     Ghosh
    0.64
     Banerjee
    0.59
    Bengal
    0.57
    Activations Density 0.145%

    No Known Activations