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. 7-GEMMASCOPE-RES-16K
    6. 9226
    Prev
    Next
    INDEX
    Explanations

    phrases indicating lengthy or ongoing discussions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 7-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_7/width_16k/average_l0_69
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Hook Layer
    7
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     doigt
    -0.65
    Portail
    -0.59
    ponses
    -0.59
    }{*}{
    -0.55
     cuivre
    -0.54
    poň
    -0.54
    uey
    -0.53
     vermelhas
    -0.53
    死的
    -0.53
    LinkId
    -0.53
    POSITIVE LOGITS
    +#+#
    0.64
     explanation
    0.58
     blah
    0.56
     monologue
    0.55
     reasons
    0.54
     lengthy
    0.53
    writeFieldEnd
    0.53
     continued
    0.53
     Philosop
    0.52
    setVerticalGroup
    0.51
    Activations Density 0.488%

    No Known Activations