© 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-2-9B
    7. Residual Stream - 16k
    9. 35-GEMMASCOPE-RES-16K
    11. 14537
    Prev
    Next
    INDEX
    Explanations

    sentences that express transitions, changes, and migration processes, particularly in the context of technology or systems

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 35-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_35/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.35.hook_resid_post
    Hook Layer
    35
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     MainAxisSize
    -0.41
    bootstrapcdn
    -0.38
    DIPSETTING
    -0.36
    fVar
    -0.34
    +#+#
    -0.34
    avras
    -0.33
    makedirs
    -0.32
    drawiam
    -0.31
    AsUp
    -0.30
    ResumeLayout
    -0.29
    POSITIVE LOGITS
     transition
    2.98
     transitioning
    2.69
     switch
    2.67
     switching
    2.66
     Transition
    2.56
     transitioned
    2.55
    transition
    2.50
     transitions
    2.48
     Switching
    2.44
    Transition
    2.41
    Activations Density 1.366%

    No Known Activations