© 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-2-2B
    7. Residual Stream - 16k
    9. 22-GEMMASCOPE-RES-16K
    11. 3164
    Prev
    Next
    INDEX
    Explanations

    programming concepts related to loading and file handling

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

    Code snippets involving "load"

    np_acts-logits-general · gemini-2.0-flash

    loading and load functions

    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
    DeleteBehavior
    -0.59
     Мексичка
    -0.59
    HasAnnotation
    -0.59
     iParam
    -0.58
     typelib
    -0.58
    tvguidetime
    -0.57
    SharedCtor
    -0.57
    ConstraintMaker
    -0.55
    KommentareTeilen
    -0.55
    setVerticalGroup
    -0.54
    POSITIVE LOGITS
     load
    3.74
     Load
    3.43
    load
    3.40
     loading
    3.26
    Load
    3.22
     LOAD
    3.10
     loaded
    2.98
     Loading
    2.96
     loads
    2.90
    LOAD
    2.88
    Activations Density 0.290%

    No Known Activations