© 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
    7. Residual Stream - 16k
    9. 30-GEMMASCOPE-RES-16K
    11. 12621
    Prev
    Next
    INDEX
    Explanations

    elements related to family dynamics and personal relationships

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

    Follows verbs like send, arresting, killing

    np_acts-logits-general · gemini-2.0-flash

    actions and states of being

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 30-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_30/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.30.hook_resid_post
    Hook Layer
    30
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     a
    -0.35
     son
    -0.29
     Lands
    -0.29
    ada
    -0.28
     cricketer
    -0.28
    DIRS
    -0.28
    的那个
    -0.28
    gre
    -0.28
     Minister
    -0.28
    兩種
    -0.27
    POSITIVE LOGITS
     nahilalakip
    0.90
    tagHelperRunner
    0.90
    脚注の使い方
    0.86
    WithIOException
    0.85
    parsedMessage
    0.82
     كومونز
    0.77
    SharedCtor
    0.75
    المكان
    0.75
     these
    0.74
     snippetHide
    0.73
    Activations Density 1.014%

    No Known Activations