© 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-2-2B
    4. Residual Stream - 16k
    5. 9-GEMMASCOPE-RES-16K
    6. 14953
    Prev
    Next
    INDEX
    Explanations

    conditional statements and comparisons between numerical values

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_9/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 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
    abestanden
    -0.81
    TabStop
    -0.70
    FXML
    -0.68
    tanleria
    -0.67
    الدراسه
    -0.63
    setVerticalGroup
    -0.62
     doubtnut
    -0.62
    styleable
    -0.62
     INTERESAR
    -0.61
     متعلقه
    -0.61
    POSITIVE LOGITS
     AssemblyCulture
    0.64
     AssemblyVersion
    0.51
    AccessFile
    0.50
     lavoratori
    0.48
    下载附件
    0.47
     inégal
    0.47
     >=",
    0.46
     confronti
    0.46
     casó
    0.46
    GEBURTSDATUM
    0.42
    Activations Density 0.439%

    No Known Activations