© 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. 14-GEMMASCOPE-RES-16K
    11. 10415
    Prev
    Next
    INDEX
    Explanations

    instances of possessive relationships and familial connections

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 14-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_14/width_16k/average_l0_84
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.14.hook_resid_post
    Hook Layer
    14
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     OMITTED
    -0.59
    thenReturn
    -0.53
    IntoConstraints
    -0.53
    InjectMocks
    -0.52
    +#+#
    -0.52
     BitmapFactory
    -0.52
     OnInit
    -0.51
     VizieR
    -0.51
     snippetHide
    -0.51
     sóng
    -0.51
    POSITIVE LOGITS
    ArrowToggle
    0.57
    kháu
    0.53
    OrBuilder
    0.50
    sidemargin
    0.49
    AsUp
    0.49
    tdessen
    0.49
    loway
    0.47
     &___
    0.47
     AssemblyCompany
    0.47
    CastException
    0.47
    Activations Density 1.163%

    No Known Activations