© 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. 18-GEMMASCOPE-RES-16K
    6. 9731
    Prev
    Next
    INDEX
    Explanations

    phrases related to legal decisions and their implications

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

    preceding a clause or statement

    np_acts-logits-general · gemini-2.0-flash

    not permitting or accepting

    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
    moiselle
    -0.52
    uteri
    -0.51
     FEE
    -0.51
     impati
    -0.50
    umbersome
    -0.49
    atten
    -0.49
    reich
    -0.48
     cải
    -0.48
    enido
    -0.48
    ukunft
    -0.47
    POSITIVE LOGITS
     justify
    1.20
     justifies
    1.11
     justification
    1.06
     justified
    1.04
     gius
    1.02
     justifying
    1.01
     legitim
    0.95
    justify
    0.93
     justific
    0.92
     legiti
    0.87
    Activations Density 0.476%

    No Known Activations