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. 10092
    Prev
    Next
    INDEX
    Explanations

    technical terms related to software or programming concepts

    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
    ():
    
    -0.59
    hobia
    -0.54
    </h2>
    -0.54
    levance
    -0.52
    :]:
    -0.52
    (){
    
    -0.51
    _();
    -0.48
    ())).
    -0.48
    `}
    -0.47
    ‎
    -0.47
    POSITIVE LOGITS
    ValueStyle
    1.08
     فريبيس
    1.01
     صوتيه
    0.91
    tagHelperRunner
    0.83
     <<<<<<<<<<<<<<
    0.83
     noDo
    0.79
    enumii
    0.79
    consulté
    0.78
    webElement
    0.75
    EndContext
    0.75
    Activations Density 0.915%

    No Known Activations