© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 13313
    Prev
    Next
    INDEX
    Explanations

    themes of shared experiences and feelings among individuals

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

    Expressing shared experiences or feelings

    np_acts-logits-general · gemini-2.0-flash

    same or similar

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ativistic
    -0.54
     permits
    -0.54
     <<<<<<<<<<<<<<
    -0.53
    béco
    -0.52
     Permits
    -0.48
     setPrice
    -0.47
    RequestMapping
    -0.46
     obowią
    -0.46
    styleType
    -0.46
     Reglas
    -0.46
    POSITIVE LOGITS
     ujednoznacz
    0.43
     CanadaChoose
    0.34
    ckså
    0.32
    Попис
    0.32
    同様
    0.32
     Audiodateien
    0.31
    Same
    0.30
     swap
    0.30
    oneofs
    0.29
    igshid
    0.29
    Activations Density 0.211%

    No Known Activations