© 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. 3079
    Prev
    Next
    INDEX
    Explanations

    financial terminology and concepts related to regulations

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

    Passive voice verbs

    np_acts-logits-general · gemini-2.0-flash

    actions taken

    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
     überlegen
    -0.59
    locating
    -0.58
     supérieurs
    -0.58
    andExpect
    -0.56
     réalis
    -0.55
     pauvres
    -0.55
     pères
    -0.53
     voud
    -0.52
     fizer
    -0.52
    paying
    -0.52
    POSITIVE LOGITS
     taken
    1.49
     handled
    1.37
     eaten
    1.30
     delivered
    1.29
     executed
    1.28
     brought
    1.27
     done
    1.24
     implemented
    1.22
     dealt
    1.20
     held
    1.20
    Activations Density 3.126%

    No Known Activations