© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 1-GEMMASCOPE-RES-16K
    11. 6753
    Prev
    Next
    INDEX
    Explanations

    references to academic publications, particularly in physics journals

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 1-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_1/width_16k/average_l0_102
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.1.hook_resid_post
    Hook Layer
    1
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     propOrder
    -0.77
     المعيارى
    -0.70
    SuppressLint
    -0.69
     mortgagee
    -0.62
     venuto
    -0.61
    jig
    -0.61
     nakalista
    -0.60
     ComVisible
    -0.59
    SBATCH
    -0.58
    wpi
    -0.58
    POSITIVE LOGITS
    IP
    0.69
     envelope
    0.66
    verifyException
    0.62
     IP
    0.62
     vic
    0.59
    featureID
    0.59
    ❹
    0.57
     envelopes
    0.55
    IPs
    0.55
     pala
    0.54
    Activations Density 2.158%

    No Known Activations