© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 54215
    Prev
    Next
    INDEX
    Explanations

    phrases related to legal status and issues surrounding citizenship and immigration

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

    cannot not no refuse

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ujednoznacz
    -0.41
     مشين
    -0.39
    SerializedSize
    -0.36
     Paglinawan
    -0.36
     logiciels
    -0.35
    )​
    -0.35
    يميديا
    -0.35
    hoeddwyd
    -0.35
    ​,
    -0.34
     VIAF
    -0.34
    POSITIVE LOGITS
    AnimationsModule
    0.47
    MLLoader
    0.45
    StructEnd
    0.41
    vine
    0.41
     fixing
    0.41
     FBref
    0.40
    ceptable
    0.40
    bastien
    0.39
    iertes
    0.38
    fixing
    0.38
    Activations Density 0.241%

    No Known Activations