Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 16-GEMMASCOPE-RES-16K
    6. 12399
    Prev
    Next
    INDEX
    Explanations

    instances of consistency and reliability in various contexts

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

    "Consistent" followed by "with"

    np_acts-logits-general · gemini-2.0-flash

    consistent with

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    kuuta
    -0.81
    PMailer
    -0.76
    reactstrap
    -0.76
    ValueStyle
    -0.72
    WindowConstants
    -0.68
     setOpen
    -0.65
     NavController
    -0.65
    ########.
    -0.62
    ArrowToggle
    -0.61
     []:
    -0.60
    POSITIVE LOGITS
     Consistency
    0.98
     inconsistency
    0.95
    sistency
    0.92
     inconsistent
    0.91
    Consistency
    0.90
     inconsistencies
    0.87
     consistency
    0.83
     subordin
    0.82
    consistency
    0.77
     cdti
    0.76
    Activations Density 0.144%

    No Known Activations