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. 16118
    Prev
    Next
    INDEX
    Explanations

    code elements related to error handling and response encoding

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

    Code-related terms after symbols

    np_acts-logits-general · gemini-2.0-flash

    Convert or safe operations

    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
    WaitGroup
    -0.66
    OGND
    -0.59
     resourceCulture
    -0.57
    WebVitals
    -0.55
    crollView
    -0.55
    bootstrapcdn
    -0.52
    下载附件
    -0.52
     GlobalKey
    -0.51
     onView
    -0.51
    +:+
    -0.51
    POSITIVE LOGITS
     Conversions
    0.65
     Converts
    0.65
    safe
    0.65
     convert
    0.64
     safe
    0.64
    وفاته
    0.58
     converts
    0.58
     safely
    0.58
     bezpiecz
    0.57
     Chwiliwch
    0.57
    Activations Density 0.299%

    No Known Activations