© 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. 5376
    Prev
    Next
    INDEX
    Explanations

    formulations involving the verb "to be" and its various grammatical forms

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

    Preceding "a" or "an"

    np_acts-logits-general · gemini-2.0-flash

    as a

    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
     two
    -0.76
     something
    -0.70
    the
    -0.68
    something
    -0.67
    two
    -0.66
     
    -0.63
     another
    -0.62
     the
    -0.59
    another
    -0.59
    Two
    -0.58
    POSITIVE LOGITS
    enumii
    1.04
     AspNetCore
    1.03
    tagHelperRunner
    1.02
    IUrlHelper
    0.93
     Мексичка
    0.92
     ainfi
    0.86
    enumi
    0.86
    \{\\
    0.85
    saraba
    0.84
     tantôt
    0.82
    Activations Density 0.324%

    No Known Activations