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. 22-GEMMASCOPE-RES-16K
    6. 8324
    Prev
    Next
    INDEX
    Explanations

    elements related to HTTP response handling in code

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

    Code snippets with "res" assignment

    np_acts-logits-general · gemini-2.0-flash

    res in code contexts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    BeginInit
    -0.76
     nakalista
    -0.73
    rungsseite
    -0.71
    ]--;
    -0.68
    Personendaten
    -0.63
    RegistryLite
    -0.63
     насељу
    -0.63
    ".
    
    -0.62
     ſind
    -0.62
    ]<<"
    -0.61
    POSITIVE LOGITS
     resourceCulture
    0.53
     commerciaux
    0.51
     res
    0.49
    énario
    0.48
     NgModule
    0.47
     iulie
    0.46
    zepte
    0.45
    CGContext
    0.43
    XLSX
    0.43
     visitare
    0.42
    Activations Density 0.047%

    No Known Activations