© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 22-GEMMASCOPE-RES-16K
    11. 5690
    Prev
    Next
    INDEX
    Explanations

    instances of punctuation or sentence endings

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_22/width_16k/average_l0_123
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     CreateTagHelper
    -0.44
    hoeddwyd
    -0.38
    뀐
    -0.36
    Kaieteur
    -0.35
     hej
    -0.35
    ieteur
    -0.35
     insuffisamment
    -0.35
     adoption
    -0.34
     Leech
    -0.34
     indiri
    -0.34
    POSITIVE LOGITS
    ammans
    0.47
    GEBURTSDATUM
    0.47
    WillAppear
    0.47
     kaarangay
    0.45
    íncia
    0.43
     queued
    0.42
    webElement
    0.42
    disposing
    0.41
    pēc
    0.41
    matchCondition
    0.41
    Activations Density 0.022%

    No Known Activations