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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 11-GEMMASCOPE-RES-16K
    6. 5130
    Prev
    Next
    INDEX
    Explanations

    phrases related to behaviors and responses in children's development and parenting

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 11-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_11/width_16k/average_l0_118
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Hook Layer
    11
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    quanto
    -0.32
    angliski
    -0.28
     sla
    -0.28
    逐
    -0.28
     فول
    -0.27
     ta
    -0.26
    ില
    -0.25
    Ta
    -0.25
     scri
    -0.25
     fly
    -0.25
    POSITIVE LOGITS
    ConstraintMaker
    0.71
     ſind
    0.66
    InvalidProtocol
    0.65
     ddelwed
    0.64
    iſchen
    0.63
     fashiola
    0.63
     imagui
    0.62
     GenerationType
    0.62
     好文分享
    0.62
    <unused79>
    0.61
    Activations Density 0.810%

    No Known Activations