© 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. 12852
    Prev
    Next
    INDEX
    Explanations

    statements and terminology related to legal claims

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

    "claim" or "claims"

    np_acts-logits-general · gemini-2.0-flash

    claim for or that

    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
    randomUUID
    -0.84
     فريبيس
    -0.84
    IUrlHelper
    -0.76
    XmlSchema
    -0.74
    ChildScrollView
    -0.72
    ]=>
    -0.72
    ticides
    -0.71
    __":
    -0.71
    AlterField
    -0.71
     htons
    -0.70
    POSITIVE LOGITS
     Claims
    1.28
     claims
    1.25
     Claim
    1.22
     claim
    1.19
    Claims
    1.12
     CLAIMS
    1.10
     CLAIM
    1.09
    claims
    1.09
    Claim
    1.06
    claim
    1.03
    Activations Density 0.148%

    No Known Activations