© 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
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 2585
    Prev
    Next
    INDEX
    Explanations

    variations of the word "involvement," particularly in the context of parental involvement and its impact

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

    phrases related to personal guidance or helping someone with a task.

    oai_token-act-pair · claude-3-5-haiku-20241022Triggered by @neilrathi
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_16k/average_l0_68
    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
    يكب
    -0.49
    ChildScrollView
    -0.45
    期刊论文
    -0.42
     policías
    -0.40
    extAlignment
    -0.40
     secundaria
    -0.38
     guerras
    -0.38
     ujednoznacz
    -0.38
     zdrowia
    -0.38
     chercheurs
    -0.38
    POSITIVE LOGITS
    awtextra
    0.59
     monitoring
    0.59
     supervision
    0.56
     supervising
    0.56
    ftagPool
    0.55
    +#+#
    0.54
     monitor
    0.53
    TagMode
    0.51
     assistance
    0.50
     supervisory
    0.49
    Activations Density 0.287%

    No Known Activations