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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 16-GEMMASCOPE-RES-16K
    6. 36
    Prev
    Next
    INDEX
    Explanations

    instances of conditions or factors leading to significant events or combinations in a scientific context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    that can be used to start a sentence

    np_acts-logits-general · gemini-2.0-flash

    listed points in texts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/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.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    principalTable
    -0.76
     loosing
    -0.67
     idéia
    -0.67
     ){
    -0.64
     recieve
    -0.64
     muß
    -0.63
     :
    -0.63
     definately
    -0.63
    faßt
    -0.63
    iteritems
    -0.61
    POSITIVE LOGITS
     Afterward
    0.95
    . 
    0.80
     XNUMX
    0.75
    Suppose
    0.74
     whatnot
    0.71
     ?
    0.70
     afterward
    0.68
     onboarding
    0.65
     ;
    0.64
    ‍
    0.63
    Activations Density 0.305%

    No Known Activations