© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 12-GEMMASCOPE-RES-16K
    11. 12174
    Prev
    Next
    INDEX
    Explanations

    phrases indicating uncertainty or unknown information

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 12-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_12/width_16k/average_l0_130
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    aarrggbb
    -0.43
    ophageal
    -0.40
    dentes
    -0.40
    angana
    -0.40
    Становништво
    -0.40
    VersionUID
    -0.40
    ReusableCell
    -0.39
    udia
    -0.38
    binant
    -0.38
    AddTagHelper
    -0.37
    POSITIVE LOGITS
     unknown
    0.75
     Unknown
    0.65
     UNKNOWN
    0.60
     unknowns
    0.60
     unclear
    0.59
     undetermined
    0.59
    unknown
    0.58
    Unknown
    0.55
     unknow
    0.55
     неизвест
    0.54
    Activations Density 0.994%

    No Known Activations