© 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. 15966
    Prev
    Next
    INDEX
    Explanations

    phrases indicating a possessive or relational context

    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
    migrationBuilder
    -0.71
    MessageTagHelper
    -0.70
     Meksiku
    -0.69
    UnusedPrivate
    -0.67
    ysuckle
    -0.66
     kohdetta
    -0.66
    NameInMap
    -0.65
    ()]
    -0.63
    ۜ
    -0.63
    twimg
    -0.63
    POSITIVE LOGITS
     الاطلاع
    0.56
    latego
    0.56
    ẓ
    0.55
     eccl
    0.53
    (&_
    0.52
    animaux
    0.50
    equalTo
    0.49
    Cust
    0.49
     jako
    0.48
     ecles
    0.48
    Activations Density 0.047%

    No Known Activations