© 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. 27-GEMMASCOPE-RES-16K
    6. 8837
    Prev
    Next
    INDEX
    Explanations

    assertions and statements regarding personal opinions or beliefs

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 27-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_27/width_16k/average_l0_118
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.27.hook_resid_post
    Hook Layer
    27
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    rungsseite
    -1.05
     queſta
    -0.93
    <unused3>
    -0.88
    <unused41>
    -0.88
    <unused14>
    -0.88
    <pad>
    -0.88
    <unused43>
    -0.88
    <unused51>
    -0.88
    [@BOS@]
    -0.88
    <unused8>
    -0.88
    POSITIVE LOGITS
    ,
    0.59
    ?
    0.49
    ...
    0.41
    …
    0.41
    ……
    0.38
    ....
    0.34
    ….
    0.34
    ......
    0.33
    ..
    0.32
    .......
    0.32
    Activations Density 0.338%

    No Known Activations