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. 8-GEMMASCOPE-RES-16K
    6. 6342
    Prev
    Next
    INDEX
    Explanations

    boolean values and conditions related to settings or configurations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 8-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_8/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.hook_resid_post
    Hook Layer
    8
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     tartalomajánló
    -0.90
    |}{$
    -0.69
    Datuak
    -0.60
     Fora
    -0.60
     sumpay
    -0.59
     }{@
    -0.56
     MainAxisSize
    -0.55
    awtextra
    -0.55
    findpost
    -0.54
    Халык
    -0.54
    POSITIVE LOGITS
    EndGlobalSection
    0.53
    GEBURTSDATUM
    0.52
    ponses
    0.51
    queryInterface
    0.51
    omitempty
    0.50
    atimes
    0.47
     CreateTagHelper
    0.47
    ,
    0.47
    styleable
    0.47
     cref
    0.46
    Activations Density 0.235%

    No Known Activations