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-2-2B
    4. Residual Stream - 16k
    5. 11-GEMMASCOPE-RES-16K
    6. 7094
    Prev
    Next
    INDEX
    Explanations

    function definitions and their parameters in code

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 11-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_11/width_16k/average_l0_80
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Hook Layer
    11
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     UIImage
    -0.53
     En
    -0.49
    -
    -0.48
     here
    -0.46
    <sup>
    -0.46
    En
    -0.45
     Al
    -0.45
    de
    -0.44
     hereby
    -0.44
    al
    -0.44
    POSITIVE LOGITS
     ExecuteAsync
    1.12
     Infórmanos
    0.97
    脚注の使い方
    0.95
    Geplaatst
    0.94
    原始内容存档于
    0.93
     disambiguazione
    0.92
    zzleHttp
    0.91
    tagHelperRunner
    0.91
     autorytatywna
    0.90
    Personendaten
    0.89
    Activations Density 0.101%

    No Known Activations