© 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. 28-GEMMASCOPE-RES-16K
    6. 8975
    Prev
    Next
    INDEX
    Explanations

    words related to cream and creamy substances

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

    Tokens starting with "cre" or related to creams

    np_acts-logits-general · gemini-2.0-flash

    words starting with cre

    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
    ะ
    -0.43
    bindValue
    -0.42
     Sam
    -0.38
     agg
    -0.38
    Geografi
    -0.36
     parti
    -0.35
     par
    -0.35
     partial
    -0.35
     Samuel
    -0.35
    addGroup
    -0.35
    POSITIVE LOGITS
    Cre
    0.74
     cre
    0.73
    cre
    0.70
     Cre
    0.68
     CRE
    0.65
    CRE
    0.65
     surla
    0.59
     whoſe
    0.59
    Dre
    0.58
     Theſe
    0.58
    Activations Density 0.100%

    No Known Activations