© 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. 18-GEMMASCOPE-RES-16K
    11. 8975
    Prev
    Next
    INDEX
    Explanations

    legal terminology and phrases related to court cases and judicial procedures

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

    "here" or its translations

    np_acts-logits-general · gemini-2.0-flash

    here

    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
    GraphicsUnit
    -0.73
    [++
    -0.57
    "):
    -0.53
    gorm
    -0.52
     ferner
    -0.51
    """.
    -0.51
    }`).
    -0.50
    stdc
    -0.50
     nahilalakip
    -0.50
     nonatomic
    -0.50
    POSITIVE LOGITS
     here
    1.48
    here
    1.30
     ours
    1.26
     ici
    1.14
    今回は
    1.09
    Here
    1.07
     здесь
    1.06
    这里是
    1.03
    Ours
    1.02
     aquí
    1.01
    Activations Density 0.747%

    No Known Activations