© 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. 22-GEMMASCOPE-RES-16K
    6. 14728
    Prev
    Next
    INDEX
    Explanations

    phrases that indicate outcomes or results from actions or events

    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
    staticmethod
    -0.65
    ChildScrollView
    -0.53
     BrowserModule
    -0.51
     Chriftian
    -0.50
     cotone
    -0.49
     princí
    -0.48
    Bakgrunnsstoff
    -0.47
    cachor
    -0.47
    Avan
    -0.47
    getSupport
    -0.47
    POSITIVE LOGITS
     causes
    0.73
     resulting
    0.73
     caused
    0.67
    resulting
    0.65
     result
    0.65
     causing
    0.65
    导致
    0.62
    caused
    0.61
     cause
    0.60
     Causes
    0.60
    Activations Density 0.513%

    No Known Activations