© 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. 6-GEMMASCOPE-RES-16K
    11. 5903
    Prev
    Next
    INDEX
    Explanations

    technical specifications and features of materials and products

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 6-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_6/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.6.hook_resid_post
    Hook Layer
    6
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    AndEndTag
    -0.75
    InSection
    -0.69
     дописавши
    -0.67
     MessageBoxIcon
    -0.65
    ^(@)
    -0.65
    windowFixed
    -0.64
    horabuena
    -0.63
     tetrachloride
    -0.61
     AttributeSet
    -0.61
    DockStyle
    -0.60
    POSITIVE LOGITS
     continúas
    0.53
    CrossRef
    0.50
     Roskov
    0.47
     nakalista
    0.47
    hysema
    0.47
    Demografia
    0.45
    keyboardType
    0.45
    ้อมูล
    0.45
    HideFlags
    0.44
    ipel
    0.44
    Activations Density 0.319%

    No Known Activations