© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 24-GEMMASCOPE-RES-16K
    11. 5490
    Prev
    Next
    INDEX
    Explanations

    sections of technical documentation and software licensing terms

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

    Code or special characters

    np_acts-logits-general · gemini-2.0-flash

    otherwise, disclaimer

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_24/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    LookAnd
    -0.69
    openzeppelin
    -0.68
    SequentialGroup
    -0.63
     kaarangay
    -0.58
    twimg
    -0.54
     FetchType
    -0.51
    JspWriter
    -0.49
    AutoScaleMode
    -0.49
    tinyos
    -0.48
    mockMvc
    -0.48
    POSITIVE LOGITS
     altrimenti
    0.55
    hidupan
    0.53
     otherwise
    0.52
    ientôt
    0.49
     allora
    0.47
     variés
    0.47
     Otherwise
    0.46
     ketentuan
    0.46
     ilustracja
    0.46
     możliwe
    0.46
    Activations Density 0.011%

    No Known Activations