© 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. 16-GEMMASCOPE-RES-16K
    11. 3223
    Prev
    Next
    INDEX
    Explanations

    technical terms and methodologies related to image processing and analysis

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Image processing / gradient operators

    np_acts-logits-general · gemini-2.0-flash

    connected-component labeling

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     holo
    -0.53
    Redirection
    -0.51
     redirection
    -0.51
    versa
    -0.49
     <>",
    -0.49
     redirected
    -0.48
     SqlCommand
    -0.48
    licative
    -0.48
    glTexCoord
    -0.47
    slot
    -0.46
    POSITIVE LOGITS
    InitVars
    0.71
    BeginContext
    0.66
    +:+
    0.63
    цездатний
    0.63
    principalTable
    0.61
    #+#
    0.57
    >//
    0.57
     فريبيس
    0.55
     jadx
    0.54
    UObject
    0.53
    Activations Density 0.801%

    No Known Activations