© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 2-GEMMASCOPE-RES-16K
    6. 5800
    Prev
    Next
    INDEX
    Explanations

    phrases indicating agency or authorship in a text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_2/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.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ſind
    -1.23
     ſche
    -1.20
    <unused43>
    -1.16
    <unused51>
    -1.16
    <unused23>
    -1.16
    <unused16>
    -1.16
    <unused8>
    -1.15
    <unused14>
    -1.15
    <unused3>
    -1.15
    [@BOS@]
    -1.15
    POSITIVE LOGITS
     by
    1.27
     of
    0.91
     the
    0.80
     from
    0.73
    ↵
    0.69
     on
    0.68
     
    0.67
     in
    0.66
     with
    0.65
     for
    0.65
    Activations Density 0.254%

    No Known Activations