© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 41-GEMMASCOPE-RES-16K
    6. 9305
    Prev
    Next
    INDEX
    Explanations

    specific terms related to political and social dynamics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 41-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_41/width_16k/average_l0_113
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.41.hook_resid_post
    Hook Layer
    41
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    bootstrapcdn
    -1.63
     kasarigan
    -1.62
    featureID
    -1.53
     fashiola
    -1.52
     queſta
    -1.52
     ſind
    -1.51
     ſeyn
    -1.51
    addPreferred
    -1.49
     estekak
    -1.49
     dieſes
    -1.48
    POSITIVE LOGITS
    for
    0.32
    with
    0.31
    from
    0.28
    by
    0.27
    of
    0.27
    to
    0.22
    during
    0.22
    when
    0.19
    but
    0.18
    into
    0.18
    Activations Density 1.737%

    No Known Activations