© 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. 28-GEMMASCOPE-RES-16K
    6. 7441
    Prev
    Next
    INDEX
    Explanations

    code snippets related to string encoding and formatting

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

    Unicode and UTF encodings

    np_acts-logits-general · gemini-2.0-flash

    unicode and utf encodings

    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
     الاطلاع
    -0.47
    igshid
    -0.45
    audiovisuel
    -0.44
    culable
    -0.43
     BoxDecoration
    -0.43
     GenerationType
    -0.42
    SequentialGroup
    -0.41
     Efq
    -0.41
    LLocation
    -0.40
     Amiens
    -0.40
    POSITIVE LOGITS
     UTF
    0.64
     unicode
    0.61
     Unicode
    0.60
     utf
    0.59
    UTF
    0.57
    unicode
    0.56
    Unicode
    0.53
     charset
    0.49
    StandardCharsets
    0.47
     extranjera
    0.45
    Activations Density 1.377%

    No Known Activations