© 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. 22-GEMMASCOPE-RES-16K
    11. 3149
    Prev
    Next
    INDEX
    Explanations

    references to processes, operations, or interactions particularly in technical contexts

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

    Something "is" or something "undergoes" something

    np_acts-logits-general · gemini-2.0-flash

    state changes

    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
     means
    -0.66
    ोंने
    -0.58
    }{$\
    -0.58
     esternos
    -0.56
    means
    -0.54
     позволит
    -0.53
    ########.
    -0.53
     represents
    -0.52
     MEANS
    -0.52
     geweest
    -0.51
    POSITIVE LOGITS
     becomes
    1.25
     become
    1.07
    becomes
    1.06
     gets
    1.06
     disappears
    1.04
     undergoes
    0.96
     vanishes
    0.95
     Becomes
    0.95
     ceases
    0.90
    become
    0.89
    Activations Density 0.889%

    No Known Activations