© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 28-GEMMASCOPE-RES-16K
    11. 4220
    Prev
    Next
    INDEX
    Explanations

    phrases indicating causation or consequences

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

    Followed by ", we" or ", the"

    np_acts-logits-general · gemini-2.0-flash

    concluding Thus

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 28-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_28/width_16k/average_l0_119
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.28.hook_resid_post
    Hook Layer
    28
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    s
    -1.55
    ים
    -0.85
    ات
    -0.69
    ς
    -0.60
    URLException
    -0.57
    WriteTagHelper
    -0.56
    pherals
    -0.55
    stanbul
    -0.55
    bidities
    -0.55
    sted
    -0.53
    POSITIVE LOGITS
    o
    0.65
    er
    0.63
    <bos>
    0.63
    𝓵
    0.63
    𝓮
    0.62
    ン
    0.60
    𝓲
    0.59
    𝓭
    0.57
    𝓾
    0.54
    𝓴
    0.53
    Activations Density 2.589%

    No Known Activations