© 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. 5757
    Prev
    Next
    INDEX
    Explanations

    references to clothing items and their qualities

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

    Pronouns followed by verbs

    np_acts-logits-general · gemini-2.0-flash

    looks like

    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
    }){
    -0.45
    ereco
    -0.44
    概
    -0.42
    HomeAsUp
    -0.42
    加以
    -0.41
    yat
    -0.41
     corrid
    -0.41
    nios
    -0.40
    好感
    -0.40
    推
    -0.40
    POSITIVE LOGITS
     belonged
    0.97
     cost
    0.86
     unknownFields
    0.86
    StoryboardSegue
    0.81
     ProtoMessage
    0.79
    cost
    0.79
    belong
    0.79
     '\\;'
    0.78
     ligiloj
    0.78
     belong
    0.77
    Activations Density 0.579%

    No Known Activations