© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 15-GEMMASCOPE-RES-16K
    6. 12972
    Prev
    Next
    INDEX
    Explanations

    equal signs and requires clauses

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_15/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.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    URLException
    -0.58
    poel
    -0.56
    soort
    -0.54
    irish
    -0.53
     chì
    -0.53
     parroquia
    -0.53
     copii
    -0.52
     ActionResult
    -0.51
     colonia
    -0.51
    BeginContext
    -0.51
    POSITIVE LOGITS
     snippetHide
    0.63
     CreateTagHelper
    0.63
    invokeLater
    0.55
    /**
    0.55
     ProtoMessage
    0.53
     التس
    0.53
    extAlignment
    0.51
     }}"></
    0.50
    seni
    0.49
    __*/
    0.48
    Activations Density 0.099%

    No Known Activations