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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 22-GEMMASCOPE-RES-16K
    11. 9935
    Prev
    Next
    INDEX
    Explanations

    references to specific events or predictions with a temporal focus

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Tokens after "saw"

    np_acts-logits-general · gemini-2.0-flash

    saw, seeing, or observing events

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 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
    MethodManager
    -0.61
    ɵɵelementEnd
    -0.53
    principalColumn
    -0.53
    vora
    -0.53
    reibe
    -0.51
    onViewCreated
    -0.51
    relser
    -0.50
    venti
    -0.50
    σαι
    -0.50
     doInBackground
    -0.49
    POSITIVE LOGITS
     sees
    1.58
     saw
    1.39
    sees
    1.24
     see
    1.23
     seeing
    1.16
     Sees
    1.12
    seeing
    1.05
    saw
    1.05
    see
    1.03
     marks
    1.01
    Activations Density 0.319%

    No Known Activations