© 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. 10187
    Prev
    Next
    INDEX
    Explanations

    phrases indicating location or position within a context

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

    "in" followed by a noun

    np_acts-logits-general · gemini-2.0-flash

    phrases starting with "in"

    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
    AsUp
    -0.78
     TestBed
    -0.72
     NSCoder
    -0.66
    '},
    -0.64
     linkovi
    -0.64
     Baillargeon
    -0.63
    StructEnd
    -0.62
     gynnwys
    -0.62
    GOTREF
    -0.62
    RuleContext
    -0.60
    POSITIVE LOGITS
     fact
    1.35
     realidad
    0.92
     realtà
    0.90
     truth
    0.88
     verdade
    0.87
     effect
    0.87
     reality
    0.86
    fact
    0.85
     effetti
    0.83
     efecto
    0.82
    Activations Density 0.396%

    No Known Activations