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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 28-GEMMASCOPE-RES-16K
    6. 8972
    Prev
    Next
    INDEX
    Explanations

    legal terminology related to court proceedings and petitions

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

    legal appeals

    np_acts-logits-general · gemini-2.0-flash

    legal appeals

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 28-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_28/width_16k/average_l0_119
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.28.hook_resid_post
    Hook Layer
    28
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    PackageManager
    -0.35
    rms
    -0.35
    +#+
    -0.34
    </caption>
    -0.33
     IMS
    -0.31
    FTW
    -0.31
     tendance
    -0.30
     })
    -0.29
     generaciones
    -0.29
    áneamente
    -0.29
    POSITIVE LOGITS
     appeal
    1.32
     appeals
    1.23
     appealed
    1.22
    appeal
    1.18
     Appeal
    1.12
     APPEAL
    1.12
    Appeal
    1.11
    Appe
    1.10
     appealing
    1.00
     appellate
    0.98
    Activations Density 1.976%

    No Known Activations