© 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-2-2B
    4. Residual Stream - 16k
    5. 22-GEMMASCOPE-RES-16K
    6. 11410
    Prev
    Next
    INDEX
    Explanations

    phrases related to the accuracy and validity of information or documents

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

    Statements about accuracy, validity, or truthfulness

    np_acts-logits-general · gemini-2.0-flash

    accuracy, correctness, and validity

    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
     kasarigan
    -1.02
    Jeografia
    -0.77
     Савезне
    -0.71
     InputDecoration
    -0.69
     ostavi
    -0.67
     uintptr
    -0.64
    DockStyle
    -0.64
    ProcessEvent
    -0.63
    tvguidetime
    -0.63
    Identyfik
    -0.62
    POSITIVE LOGITS
     accurate
    1.82
    accurate
    1.42
     Accurate
    1.40
    Accurate
    1.36
     ACCUR
    1.26
     accuracy
    1.20
     valid
    1.19
     truthful
    1.16
     correct
    1.12
     inaccurate
    1.03
    Activations Density 0.673%

    No Known Activations