© 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. 36-GEMMASCOPE-RES-16K
    11. 14944
    Prev
    Next
    INDEX
    Explanations

    explicit references to actions or commands

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 36-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_36/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.36.hook_resid_post
    Hook Layer
    36
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    oredCriteria
    -0.92
    AndEndTag
    -0.88
    ftagPool
    -0.87
     للمعارف
    -0.86
     kaarangay
    -0.85
    principalColumn
    -0.84
     Normdatei
    -0.83
    verifyException
    -0.83
    enderror
    -0.80
    MLLoader
    -0.79
    POSITIVE LOGITS
    ________________
    0.79
    (
    0.76
    ================
    0.73
    ----------------
    0.72
                                   
    0.72
    ————————————————
    0.63
    http
    0.60
    Показать
    0.59
    and
    0.58
    https
    0.58
    Activations Density 0.982%

    No Known Activations