© 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. 18-GEMMASCOPE-RES-16K
    11. 11070
    Prev
    Next
    INDEX
    Explanations

    references to the Freedom of Information Act and related legislative topics

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

    "Freedom of Information" or related legal transparency

    np_acts-logits-general · gemini-2.0-flash

    freedom of information laws

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Carriera
    -0.57
     Caritas
    -0.48
     cuid
    -0.48
    ulipas
    -0.48
     الرياضيه
    -0.47
    ="//
    -0.47
     cared
    -0.47
    RectangleBorder
    -0.46
    invariant
    -0.45
    gdx
    -0.45
    POSITIVE LOGITS
     Freedom
    1.24
     FO
    1.04
    Freedom
    1.02
     freedom
    0.89
     FREEDOM
    0.88
    FO
    0.79
     RTI
    0.78
    foi
    0.77
    freedom
    0.76
     records
    0.72
    Activations Density 0.195%

    No Known Activations