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. 17-GEMMASCOPE-RES-16K
    6. 13337
    Prev
    Next
    INDEX
    Explanations

    academic and sporting contexts related to teams and their performance in competitions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 17-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_17/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.17.hook_resid_post
    Hook Layer
    17
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     araw
    -0.46
    Subview
    -0.44
    lə
    -0.41
     dello
    -0.41
    Jegyzetek
    -0.38
    jaus
    -0.38
     foule
    -0.38
    núť
    -0.37
    chis
    -0.37
     ko
    -0.36
    POSITIVE LOGITS
    ArgsConstructor
    1.00
     season
    0.96
    IUrlHelper
    0.90
     betweenstory
    0.86
     seasons
    0.86
    season
    0.84
     متعلقه
    0.82
    AddTagHelper
    0.81
    Datuak
    0.81
     صوتيه
    0.80
    Activations Density 0.188%

    No Known Activations