© 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-IT
    4. Residual Stream - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 101469
    Prev
    Next
    INDEX
    Explanations

    technical terms and functions related to programming

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    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
    XmlAccessType
    -0.71
    RTLR
    -0.69
    Ӕ
    -0.64
     pinulongan
    -0.63
     AssemblyCulture
    -0.62
    └──
    -0.57
     linkovi
    -0.56
     ErrIntOverflow
    -0.54
     Мексичка
    -0.53
    expandindo
    -0.52
    POSITIVE LOGITS
    LayoutInflater
    0.41
     Initially
    0.40
    Initially
    0.36
     initially
    0.35
     LayoutInflater
    0.33
    initial
    0.32
     skjer
    0.32
    Organisator
    0.32
     awakeFromNib
    0.32
    constructor
    0.31
    Activations Density 0.000%

    No Known Activations