© 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
    4. Residual Stream - 16k
    5. 27-GEMMASCOPE-RES-16K
    6. 9345
    Prev
    Next
    INDEX
    Explanations

    instances of the word "when" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 27-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_27/width_16k/average_l0_118
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.27.hook_resid_post
    Hook Layer
    27
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    NameInMap
    -0.73
    PerformLayout
    -0.72
     Wicidata
    -0.60
    WireFormatLite
    -0.59
    PreferredItem
    -0.58
    iastes
    -0.54
     MainAxisSize
    -0.54
     OFDb
    -0.53
    hicles
    -0.52
    Württemberg
    -0.52
    POSITIVE LOGITS
    SequentialGroup
    0.50
     the
    0.49
     we
    0.46
     they
    0.44
    rungsseite
    0.43
    URLException
    0.41
     there
    0.40
    kijken
    0.38
     it
    0.36
     بگ
    0.35
    Activations Density 0.336%

    No Known Activations