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-2-9B
    4. Residual Stream - 16k
    5. 21-GEMMASCOPE-RES-16K
    6. 5684
    Prev
    Next
    INDEX
    Explanations

    technical specifications and measurements related to scientific evidence

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_21/width_16k/average_l0_129
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    +:+
    -0.42
     tages
    -0.37
    EMPL
    -0.36
    <eos>
    -0.36
    richTextPanel
    -0.35
    ypep
    -0.35
     Wolf
    -0.34
     ста
    -0.34
    DebuggerNonUser
    -0.33
     Wald
    -0.33
    POSITIVE LOGITS
     autorytatywna
    0.96
     snippetHide
    0.74
    rungsseite
    0.74
    afficheront
    0.70
    ंदीखरीदारी
    0.69
     Roskov
    0.67
    ագրություններ
    0.66
     Савезне
    0.65
    TypedDataSet
    0.64
    
    0.63
    Activations Density 0.538%

    No Known Activations