© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 5284
    Prev
    Next
    INDEX
    Explanations

    interactions and exchanges among individuals, particularly those involving consent or mutual understanding

    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
    ChildScrollView
    -0.76
    يكب
    -0.68
     فريبيس
    -0.66
    expandindo
    -0.65
    \{\\
    -0.64
     متعلقه
    -0.62
     виправивши
    -0.62
    XmlAccessType
    -0.61
    HostException
    -0.58
     Berto
    -0.57
    POSITIVE LOGITS
     signals
    0.52
     INDIC
    0.51
     cue
    0.51
     cues
    0.51
     indication
    0.48
     vibe
    0.47
    bitField
    0.45
    ReusableCell
    0.44
     signaling
    0.44
     Signals
    0.44
    Activations Density 0.237%

    No Known Activations