© 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. 7634
    Prev
    Next
    INDEX
    Explanations

    expressions of realization and belief

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

    followed by a clause starting with "that"

    np_acts-logits-general · gemini-2.0-flash

    belief, realization, conviction

    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
    them
    -0.64
    him
    -0.59
    Them
    -0.58
     Acerca
    -0.50
     étant
    -0.50
     lui
    -0.50
     henne
    -0.48
    Him
    -0.47
     ihn
    -0.46
    彼の
    -0.45
    POSITIVE LOGITS
     they
    2.04
     we
    1.82
     there
    1.80
     it
    1.38
     he
    1.32
     you
    1.25
     she
    1.23
    there
    1.07
     nobody
    1.01
     они
    1.00
    Activations Density 0.484%

    No Known Activations