© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 18-GEMMASCOPE-RES-16K
    11. 4309
    Prev
    Next
    INDEX
    Explanations

    technical descriptions of modifications or characteristics related to surface structure and shape

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

    height, dimension, or surface

    np_acts-logits-general · gemini-2.0-flash

    height, surface, dimensional, embossed

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Datuak
    -0.60
     lenker
    -0.58
    SharedCtor
    -0.57
    HtmlAttribute
    -0.54
     Johansen
    -0.54
     Precambrian
    -0.53
    Extinguishing
    -0.51
    DebuggerNonUser
    -0.51
     fusible
    -0.51
     acetyl
    -0.51
    POSITIVE LOGITS
     height
    1.21
     raised
    1.18
     Height
    1.06
     Raised
    1.05
    height
    1.04
    Raised
    0.99
     heights
    0.96
     raising
    0.96
     elevation
    0.96
     raise
    0.96
    Activations Density 0.468%

    No Known Activations