© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 37-GEMMASCOPE-RES-16K
    6. 4820
    Prev
    Next
    INDEX
    Explanations

    terms related to smoothness and transitions in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 37-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_37/width_16k/average_l0_124
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.37.hook_resid_post
    Hook Layer
    37
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Partager
    -0.31
    twimg
    -0.31
    Static
    -0.27
     autrement
    -0.27
    łk
    -0.27
     indag
    -0.25
    ünf
    -0.25
    delse
    -0.25
     mandiri
    -0.25
     échelle
    -0.25
    POSITIVE LOGITS
     smooth
    3.19
     Smooth
    2.94
    smooth
    2.89
    Smooth
    2.84
     smoothness
    2.77
     smoother
    2.72
     smoothly
    2.58
     SMO
    2.36
     smoothed
    2.28
     smoothing
    2.22
    Activations Density 0.525%

    No Known Activations