© 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-IT
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 10835
    Prev
    Next
    INDEX
    Explanations

    commas used to separate clauses or items in a list

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

    Follows a comma

    np_acts-logits-general · gemini-2.0-flash

    comma followed by verbs or conjunctions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91
    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
     feroit
    -0.38
    adaptiveStyles
    -0.37
     AssemblyTitle
    -0.36
     avoient
    -0.34
    Remarque
    -0.33
    setMode
    -0.33
     expériment
    -0.33
     extreme
    -0.32
     diámetro
    -0.32
     exteriores
    -0.31
    POSITIVE LOGITS
     kasarigan
    0.58
    withIdentifier
    0.57
    middels
    0.57
    ,$_
    0.57
    ,'\
    0.54
    spinal
    0.54
    <?
    0.53
    brigens
    0.53
    ,-\
    0.53
    iteracy
    0.52
    Activations Density 0.332%

    No Known Activations