© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 16-GEMMASCOPE-RES-16K
    11. 5414
    Prev
    Next
    INDEX
    Explanations

    narratives regarding legal proceedings and jury dynamics

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

    media coverage or publicity

    np_acts-logits-general · gemini-2.0-flash

    media coverage and publicity

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    planung
    -0.51
    currentColor
    -0.47
    Proyectos
    -0.46
     谱
    -0.45
     gegründet
    -0.45
    ുടെ
    -0.43
     strutture
    -0.43
     kwaliteit
    -0.42
     piante
    -0.42
     برانيه
    -0.42
    POSITIVE LOGITS
     publicity
    1.40
     media
    1.12
     Publicity
    1.10
     public
    1.05
     publi
    1.02
     headlines
    1.01
     tabloid
    0.99
     médi
    0.99
     publicly
    0.98
     publicized
    0.98
    Activations Density 0.458%

    No Known Activations