Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 21-GEMMASCOPE-RES-16K
    6. 12648
    Prev
    Next
    INDEX
    Explanations

    legal terminology and processes related to appeals and court decisions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    psum
    -0.46
    ROIT
    -0.43
     alış
    -0.41
    شفى
    -0.40
    szön
    -0.40
     maat
    -0.39
    thwaite
    -0.39
     Initializes
    -0.38
     ombro
    -0.38
     وق
    -0.38
    POSITIVE LOGITS
     appeal
    2.31
     appeals
    2.05
    appeal
    2.04
     Appeal
    2.00
    Appeal
    1.93
     appealed
    1.89
     APPEAL
    1.84
    Appe
    1.79
     Appeals
    1.78
     appealing
    1.69
    Activations Density 2.010%

    No Known Activations