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. 4-GEMMASCOPE-RES-16K
    6. 15857
    Prev
    Next
    INDEX
    Explanations

    references to method calls or class inheritance in programming

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 4-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_4/width_16k/average_l0_124
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.hook_resid_post
    Hook Layer
    4
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    borderBottom
    -0.56
    est
    -0.54
     kvinder
    -0.52
     subterrá
    -0.49
     autorytatywna
    -0.49
    certain
    -0.48
     szár
    -0.47
    "]];
    -0.47
    dan
    -0.47
     braccia
    -0.44
    POSITIVE LOGITS
    帖最后由
    1.07
    OGND
    0.88
    AndEndTag
    0.79
     beginnetje
    0.79
    InjectAttribute
    0.79
     HttpNotFound
    0.76
    Portail
    0.75
    invokeLater
    0.73
     bezeichneter
    0.71
     contextLoads
    0.70
    Activations Density 0.060%

    No Known Activations