© 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. 8911
    Prev
    Next
    INDEX
    Explanations

    references to political events and actions

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

    Negation or denial in legal/ethical contexts

    np_acts-logits-general · gemini-2.0-flash

    legal claims and proceedings

    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
    BeginContext
    -0.63
     Manuf
    -0.63
    heria
    -0.61
     impatience
    -0.61
     Encu
    -0.61
     الحره
    -0.60
     Sacrifice
    -0.60
    __':
    -0.59
     asso
    -0.59
    ugges
    -0.58
    POSITIVE LOGITS
     numerus
    0.55
     pursuant
    0.52
     (§
    0.51
     legally
    0.50
     art
    0.46
    falls
    0.44
     shall
    0.44
    xFFFF
    0.43
     obligatory
    0.42
     rekke
    0.42
    Activations Density 0.268%

    No Known Activations