© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 15400
    Prev
    Next
    INDEX
    Explanations

    terms related to liability and protection in legal and insurance contexts

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

    "In case of" or contingencies

    np_acts-logits-general · gemini-2.0-flash

    in case or in the event

    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
    __":
    -0.76
    __':
    -0.75
    ')")
    -0.73
    __":
    -0.72
    __':
    -0.69
    }],
    -0.65
     AspNetCore
    -0.63
    Erreferentziak
    -0.61
     defaultstate
    -0.60
    OGND
    -0.59
    POSITIVE LOGITS
    万一
    1.23
     contingencies
    1.11
     scenario
    1.08
     emergencies
    1.08
     scenarios
    1.05
     happens
    0.99
     unforeseen
    0.99
     event
    0.98
     случа
    0.97
     contingency
    0.95
    Activations Density 0.268%

    No Known Activations