© 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. 8067
    Prev
    Next
    INDEX
    Explanations

    phrases that indicate the presence and status of various conditions or issues

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

    "are" followed by an adjective

    np_acts-logits-general · gemini-2.0-flash

    are adjective/adverb

    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
     its
    -1.42
     Its
    -1.15
    Its
    -1.13
     itself
    -1.06
    its
    -1.01
    它的
    -0.95
    它
    -0.91
    itself
    -0.78
     it
    -0.74
     которое
    -0.74
    POSITIVE LOGITS
     themselves
    1.67
    themselves
    1.55
     themſelves
    1.37
    those
    1.16
     serem
    1.14
     ones
    1.12
     those
    1.10
     amelyek
    1.08
     которые
    1.05
    Those
    1.05
    Activations Density 1.068%

    No Known Activations