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. 24-GEMMASCOPE-RES-16K
    6. 4856
    Prev
    Next
    INDEX
    Explanations

    phrases related to accidents and legal/medical terms

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

    before a noun or possessive

    np_acts-logits-general · gemini-2.0-flash

    people & family roles

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Audiodateien
    -0.78
    يكب
    -0.63
    EDEFAULT
    -0.63
    Datuak
    -0.63
    المناصب
    -0.62
    DockStyle
    -0.60
     переписи
    -0.58
    CodeAttribute
    -0.58
    LayoutStyle
    -0.57
     مشين
    -0.55
    POSITIVE LOGITS
     Student
    1.25
     Player
    1.17
     Person
    1.09
    Student
    1.09
     Owner
    1.08
     Employee
    1.07
     Young
    1.06
     Parent
    1.05
    Player
    1.04
     Client
    1.04
    Activations Density 0.565%

    No Known Activations