© 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. 14-GEMMASCOPE-RES-16K
    6. 7897
    Prev
    Next
    INDEX
    Explanations

    named entities, specifically proper names and titles

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 14-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_14/width_16k/average_l0_67
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.14.hook_resid_post
    Hook Layer
    14
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    <h4>
    -0.57
    2
    -0.52
    equity
    -0.50
     Volkes
    -0.50
     koll
    -0.50
    越
    -0.48
    lewati
    -0.48
    sci
    -0.47
     createSlice
    -0.46
     pleaſure
    -0.46
    POSITIVE LOGITS
    m
    0.84
    mmm
    0.73
    mmmmmm
    0.69
    mmmm
    0.65
     tm
    0.65
    mm
    0.64
    mcm
    0.63
    𝑚
    0.63
    mum
    0.63
    mming
    0.63
    Activations Density 1.784%

    No Known Activations