© 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. 6306
    Prev
    Next
    INDEX
    Explanations

    references to historical buildings and landmarks

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

    Mentions buildings and construction

    np_acts-logits-general · gemini-2.0-flash

    built and constructed buildings

    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
    Enllaces
    -0.64
    WriteTagHelper
    -0.59
     المعيارى
    -0.56
    TabLayout
    -0.55
    nodoc
    -0.53
    wahati
    -0.53
    ########.
    -0.52
    XmlEnum
    -0.51
    InitVars
    -0.50
    Picked
    -0.50
    POSITIVE LOGITS
     erected
    1.41
     constructed
    1.21
     built
    1.13
     standing
    1.07
     Constructed
    1.02
     Built
    0.94
     stands
    0.94
    constructed
    0.94
    Built
    0.94
    built
    0.93
    Activations Density 0.268%

    No Known Activations