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

    Neuronpedia

    Jacobian LensNEW
    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. 2-GEMMASCOPE-RES-16K
    11. 7387
    Prev
    Next
    INDEX
    Explanations

    instances of the word "forget" and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_2/width_16k/average_l0_67
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    SequentialGroup
    -0.59
    UseVisualStyle
    -0.49
    否
    -0.44
    chaus
    -0.44
    setViewportView
    -0.43
    RTGC
    -0.42
    awtextra
    -0.41
    providedIn
    -0.41
     Verdad
    -0.40
     Widely
    -0.40
    POSITIVE LOGITS
     forgot
    0.64
     forgetting
    0.59
    oredCriteria
    0.57
    multicolumn
    0.56
     forgotten
    0.52
     vergeten
    0.51
     forget
    0.50
     forgets
    0.50
    moveToFirst
    0.49
     vergessen
    0.47
    Activations Density 0.144%

    No Known Activations