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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 31-GEMMASCOPE-RES-16K
    6. 13826
    Prev
    Next
    INDEX
    Explanations

    terms related to Facebook account verification and privacy settings

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

    non-English language text, particularly words and phrases in Slavic languages like Serbian and Russian.

    oai_token-act-pair · claude-4-5-haikuTriggered by @emiglarou
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 31-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_31/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.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    上的
    -0.54
    多的
    -0.47
    内的
    -0.46
     yeah
    -0.44
    有的
    -0.44
    ٌ
    -0.43
     कोई
    -0.42
     yes
    -0.42
    下的
    -0.42
     інші
    -0.41
    POSITIVE LOGITS
    IsMutable
    0.86
    StructEnd
    0.76
    ValueStyle
    0.73
    awtextra
    0.70
     defaultstate
    0.69
    XmlAccessorType
    0.68
     ویکی‌پدی
    0.66
     समीक्षाओं
    0.66
    BufferException
    0.66
     ब्रेकडाउन
    0.65
    Activations Density 0.040%

    No Known Activations