© 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. 21-GEMMASCOPE-RES-16K
    6. 3099
    Prev
    Next
    INDEX
    Explanations

    specific terms and concepts related to medical and biological terms, especially in research contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_21/width_16k/average_l0_129
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    OGND
    -0.90
    tagHelperRunner
    -0.88
    <pad>
    -0.85
    <unused41>
    -0.85
    <unused68>
    -0.85
    [@BOS@]
    -0.85
    <unused74>
    -0.84
    <unused79>
    -0.84
    <unused43>
    -0.84
    <unused42>
    -0.84
    POSITIVE LOGITS
    ↵↵
    0.75
    The
    0.70
    I
    0.63
    We
    0.59
    As
    0.57
    For
    0.56
    In
    0.55
    A
    0.55
    An
    0.54
    When
    0.53
    Activations Density 0.944%

    No Known Activations