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-2-2B
    4. Residual Stream - 16k
    5. 16-GEMMASCOPE-RES-16K
    6. 4967
    Prev
    Next
    INDEX
    Explanations

    terms related to children's physical activities and challenges

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

    preceding comparative words

    np_acts-logits-general · gemini-2.0-flash

    evaluation and perceived attractiveness

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     myſelf
    -0.75
     Efq
    -0.69
     متعلقه
    -0.67
     dafs
    -0.67
    bibfield
    -0.65
     Houſe
    -0.63
     siè
    -0.63
     CreateTagHelper
    -0.61
     Monfieur
    -0.61
    aktery
    -0.60
    POSITIVE LOGITS
     perceived
    1.00
     Perceived
    0.70
     perci
    0.61
     appealing
    0.57
     feel
    0.56
     feeling
    0.55
     dianggap
    0.54
     insuffisamment
    0.51
     attractive
    0.51
    AnimationsModule
    0.51
    Activations Density 0.324%

    No Known Activations