© 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. 28-GEMMASCOPE-RES-16K
    6. 2416
    Prev
    Next
    INDEX
    Explanations

    references to scientific figures and data

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

    Tokens before ".ref"

    np_acts-logits-general · gemini-2.0-flash

    citations and code

    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
    <unused28>
    -1.04
    <unused16>
    -1.04
    <unused41>
    -1.04
    <unused79>
    -1.04
    <unused8>
    -1.03
    <unused3>
    -1.03
    <unused14>
    -1.03
    <unused17>
    -1.03
    <pad>
    -1.03
    [@BOS@]
    -1.03
    POSITIVE LOGITS
    <h1>
    0.34
     hoved
    0.27
    .
    0.24
    <h3>
    0.24
    لينكات
    0.23
    <h2>
    0.22
    2
    0.22
    <b>
    0.21
     unidade
    0.21
    medlem
    0.21
    Activations Density 0.750%

    No Known Activations