© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 24-GEMMASCOPE-RES-16K
    11. 3694
    Prev
    Next
    INDEX
    Explanations

    patterns related to error handling in code or programming logic

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

    Code and/or equations

    np_acts-logits-general · gemini-2.0-flash

    "AS IS" BASIS, WARRANTIES OR CONDITIONS

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_24/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     broad
    -0.45
    broad
    -0.45
     gir
    -0.43
     censiti
    -0.43
     nomin
    -0.42
     вста
    -0.42
     seed
    -0.41
    <eos>
    -0.41
     inv
    -0.41
     prote
    -0.40
    POSITIVE LOGITS
    ContentAsync
    1.60
    tagHelperRunner
    1.36
    IsContent
    0.88
    RunAsync
    0.62
    脚注の使い方
    0.60
    ValueStyle
    0.58
    OCCURRED
    0.58
    +#+#
    0.57
    GOTREF
    0.54
     CreateTagHelper
    0.52
    Activations Density 0.005%

    No Known Activations