© 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-2-2B
    7. Residual Stream - 16k
    9. 24-GEMMASCOPE-RES-16K
    11. 6226
    Prev
    Next
    INDEX
    Explanations

    negative sentiments or criticisms related to various subjects

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

    figures and bibliographic entries

    np_acts-logits-general · gemini-2.0-flash

    citations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 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
     فريبيس
    -0.78
    IntoConstraints
    -0.74
     CURIAM
    -0.66
    ⓧ
    -0.63
     المعيارى
    -0.63
    TestingModule
    -0.62
    Skocz
    -0.61
     חיצוניים
    -0.59
     يتيمه
    -0.55
    makeConstraints
    -0.55
    POSITIVE LOGITS
    <bos>
    0.66
    govine
    0.66
     
    0.63
    2
    0.63
    3
    0.60
    1
    0.57
    4
    0.57
    5
    0.56
    0
    0.52
    6
    0.51
    Activations Density 0.174%

    No Known Activations