© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 22-GEMMASCOPE-RES-16K
    11. 8273
    Prev
    Next
    INDEX
    Explanations

    phrases pertaining to geographical locations and their political status

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

    "In" followed by a date or location

    np_acts-logits-general · gemini-2.0-flash

    in many contexts

    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
    GOTREF
    -0.77
    '}),
    -0.70
    OrBuilder
    -0.69
     مشين
    -0.63
     متعلقه
    -0.63
    \{\\
    -0.59
    шње
    -0.58
    *~*~
    -0.57
    AddTagHelper
    -0.57
     insuffisamment
    -0.55
    POSITIVE LOGITS
     consequence
    0.66
     connexion
    0.61
     view
    0.58
     connection
    0.50
     behalf
    0.49
    раздо
    0.48
     daß
    0.47
    ilitary
    0.47
     obedience
    0.47
     petto
    0.46
    Activations Density 0.381%

    No Known Activations