Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlogSlackPrivacy & 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. 18-GEMMASCOPE-RES-16K
    6. 10654
    Prev
    Next
    INDEX
    Explanations

    nested arrays or lists

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     _)
    -0.67
    ?')
    -0.63
    fillType
    -0.62
    ?")
    -0.61
    tagHelper
    -0.59
    buttonBar
    -0.59
    gameserver
    -0.59
    {}".
    -0.57
    \}^{
    -0.57
     co
    -0.57
    POSITIVE LOGITS
     >=",
    0.75
    énario
    0.72
    Personendaten
    0.72
     judiciales
    0.70
    omores
    0.69
    numerusform
    0.58
     policiales
    0.58
    rrggbb
    0.58
     feroit
    0.58
     amables
    0.57
    Activations Density 0.191%

    No Known Activations