© 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. 9-GEMMASCOPE-RES-16K
    6. 9372
    Prev
    Next
    INDEX
    Explanations

    patterns indicating statistical data or quantities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_9/width_16k/average_l0_100
    Prompts (Dashboard)
    24,576 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
    RTEE
    -0.53
    ImageContext
    -0.49
     iconLine
    -0.45
    dafx
    -0.43
     EnglishChoose
    -0.43
     tavo
    -0.42
    tvguidetime
    -0.41
    oltà
    -0.40
     cappuccio
    -0.40
    hawa
    -0.40
    POSITIVE LOGITS
     kasarigan
    0.60
     <<<<<<<<<<<<<<
    0.55
     InputDecoration
    0.45
    合
    0.43
     EconPapers
    0.42
    ritch
    0.41
     cale
    0.41
    #+#
    0.40
    SequentialGroup
    0.40
    ofire
    0.38
    Activations Density 0.829%

    No Known Activations