© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 22-GEMMASCOPE-RES-16K
    6. 4040
    Prev
    Next
    INDEX
    Explanations

    occurrences of code blocks or instructions related to session management and error handling

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

    Code or file paths

    np_acts-logits-general · gemini-2.0-flash

    code snippets and xml

    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
     Consistency
    -0.51
     mapStateToProps
    -0.51
    AttributeSet
    -0.50
     שוליים
    -0.49
    setVerticalGroup
    -0.48
     düğ
    -0.47
    Consistency
    -0.47
    WTA
    -0.47
    numerusform
    -0.46
     ब्रेकडाउन
    -0.46
    POSITIVE LOGITS
     GenerationType
    0.59
     Oso
    0.57
     Topping
    0.54
     CreateTagHelper
    0.53
                
    0.52
     tartalomajánló
    0.51
    ebenarnya
    0.51
     المعيارى
    0.50
     Maske
    0.49
    Topping
    0.49
    Activations Density 0.040%

    No Known Activations