© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 22-GEMMASCOPE-RES-16K
    6. 8929
    Prev
    Next
    INDEX
    Explanations

    key points or significant statements in discussions

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

    Followed by the word "is" or a similar verb

    np_acts-logits-general · gemini-2.0-flash

    what is prob of

    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
     EconPapers
    -0.80
    Has
    -0.66
    Doesn
    -0.65
    DOES
    -0.60
     Has
    -0.59
    Didn
    -0.59
    Does
    -0.58
     did
    -0.54
    does
    -0.53
     Doesn
    -0.52
    POSITIVE LOGITS
     is
    1.84
     are
    1.30
     είναι
    1.01
     là
    1.00
     adalah
    0.86
    的是
    0.85
     isComment
    0.85
     êtes
    0.84
    คือ
    0.84
    ίναι
    0.83
    Activations Density 2.862%

    No Known Activations