Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 16k
    5. 9-GEMMASCOPE-RES-16K
    6. 6388
    Prev
    Next
    INDEX
    Explanations

    terms related to urban and technical concepts

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

    after short abbreviations

    np_acts-logits-general · gemini-2.0-flash

    code abbreviations and suffixes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     myſelf
    -0.74
     itſelf
    -0.74
     $_(
    -0.68
     purpoſe
    -0.66
     pleaſure
    -0.66
    TagMode
    -0.66
     queſta
    -0.65
     $_"
    -0.64
     strconv
    -0.63
     Geiſt
    -0.63
    POSITIVE LOGITS
    hydrop
    0.39
    datab
    0.39
    icec
    0.37
     redb
    0.36
     Lights
    0.35
    datat
    0.35
     McN
    0.35
    Overs
    0.34
    icep
    0.34
     Quicks
    0.34
    Activations Density 1.505%

    No Known Activations