© 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. 10-GEMMASCOPE-RES-16K
    11. 11098
    Prev
    Next
    INDEX
    Explanations

    elements and descriptions related to visibility and transparency in contexts like design and personal attributes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_10/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ignes
    -0.59
     esist
    -0.52
     secours
    -0.51
     Righteous
    -0.47
    ี่ยน
    -0.46
    KURZBESCHREIBUNG
    -0.45
     minore
    -0.45
    SizeF
    -0.45
     jota
    -0.45
     galinha
    -0.44
    POSITIVE LOGITS
     transparency
    0.97
     transparent
    0.81
    PyExc
    0.80
     transparence
    0.80
    Personendaten
    0.80
     openness
    0.79
    Transparency
    0.76
     Transparency
    0.73
    Enllaces
    0.73
     open
    0.71
    Activations Density 0.447%

    No Known Activations