© 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. 3-GEMMASCOPE-RES-16K
    11. 5803
    Prev
    Next
    INDEX
    Explanations

    terms related to names and surnames in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    rupal
    -0.52
     صوتيه
    -0.49
    oprot
    -0.48
     trans
    -0.46
    IGraphics
    -0.46
    edicated
    -0.46
    Predecesor
    -0.46
    cshtml
    -0.45
    FACT
    -0.45
    lelő
    -0.45
    POSITIVE LOGITS
     surname
    1.61
     surnames
    1.47
    lastname
    1.43
     Surname
    1.41
    surname
    1.40
    lastName
    1.39
    LastName
    1.36
    Surname
    1.26
     LastName
    1.17
     apellido
    1.17
    Activations Density 0.452%

    No Known Activations