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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 16k
    5. 31-GEMMASCOPE-RES-16K
    6. 15614
    Prev
    Next
    INDEX
    Explanations

    terms related to cognitive impairments and concentration difficulties

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

    "Concentrate" or "concentration"

    np_acts-logits-general · gemini-2.0-flash

    concentrate, concentration

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 31-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_31/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    UrlResolution
    -0.60
    principalTable
    -0.56
     estekak
    -0.52
     незавершена
    -0.50
     Meksiku
    -0.48
     ब्रेकडाउन
    -0.43
     lebaran
    -0.43
     plegable
    -0.43
     Masyarakat
    -0.43
    CppMethod
    -0.42
    POSITIVE LOGITS
     concentration
    1.80
     Concentration
    1.63
    concentration
    1.60
    Concentration
    1.55
     concentrate
    1.55
     CONCENT
    1.51
     concentr
    1.50
    concentr
    1.48
     concentrating
    1.46
    Concentr
    1.45
    Activations Density 0.191%

    No Known Activations