© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 22-GEMMASCOPE-RES-16K
    6. 5604
    Prev
    Next
    INDEX
    Explanations

    references to image processing and related libraries

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

    Tokens following "Image" or "image"

    np_acts-logits-general · gemini-2.0-flash

    ImageMagick

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Normdatei
    -0.61
    UnusedPrivate
    -0.55
     ويكيپيديا
    -0.55
    providedIn
    -0.55
     infinitive
    -0.54
    SARA
    -0.53
     subtilis
    -0.53
    Abp
    -0.51
    Története
    -0.51
     동안
    -0.51
    POSITIVE LOGITS
     vectorielle
    0.66
    цуз
    0.58
    Magick
    0.57
     byteArray
    0.57
     Waterhouse
    0.57
    برد
    0.56
    enez
    0.55
    glycer
    0.54
     refuer
    0.53
     proyec
    0.53
    Activations Density 0.089%

    No Known Activations