© 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. 20-GEMMASCOPE-RES-16K
    6. 10043
    Prev
    Next
    INDEX
    Explanations

    terms and concepts related to recovery and rehabilitation

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

    terms related to medical recovery processes or healing.

    oai_token-act-pair · claude-3-5-haiku-20241022Triggered by @neilrathi
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_16k/average_l0_68
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    getElements
    -0.41
     openly
    -0.40
     Dirichlet
    -0.38
     Dominus
    -0.37
     push
    -0.36
     Wren
    -0.36
    Señor
    -0.36
    XAxis
    -0.35
    0
    -0.35
     role
    -0.34
    POSITIVE LOGITS
     recovery
    1.22
    Recovery
    1.17
    recovery
    1.16
     Recovery
    1.15
     RECOVERY
    1.08
     recoveries
    1.07
     recovering
    1.04
     recover
    1.03
     restoration
    1.02
     recuperación
    1.00
    Activations Density 0.167%

    No Known Activations