© 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. 12-GEMMASCOPE-RES-16K
    6. 5186
    Prev
    Next
    INDEX
    Explanations

    comparative and superlative phrases relating to intensity or quality

    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
    labelledby
    -0.42
     easy
    -0.42
     useState
    -0.40
     easily
    -0.36
    writeObject
    -0.36
    談社
    -0.35
     Kram
    -0.35
    !
    -0.35
    .
    -0.34
    createNewFile
    -0.34
    POSITIVE LOGITS
     CreateTagHelper
    0.85
    OGND
    0.79
    Lähteet
    0.68
     ainfi
    0.56
     Majefty
    0.55
     CanadaChoose
    0.55
     pinulongan
    0.54
     estekak
    0.52
     abſ
    0.52
     Eſ
    0.51
    Activations Density 0.772%

    No Known Activations