© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 1-GEMMASCOPE-RES-16K
    6. 11318
    Prev
    Next
    INDEX
    Explanations

    the word "direct" and its variations, indicating a focus on concepts of direction or indication

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 1-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_1/width_16k/average_l0_102
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.1.hook_resid_post
    Hook Layer
    1
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     calendriers
    -0.65
     بيها
    -0.64
    intios
    -0.60
    FormatException
    -0.57
     beginnetje
    -0.53
     Langer
    -0.53
     Pless
    -0.52
    دى
    -0.51
    OGND
    -0.51
    acteria
    -0.50
    POSITIVE LOGITS
     direct
    2.35
    direct
    2.27
     Direct
    2.15
    Direct
    2.14
     DIRECT
    1.84
    DIRECT
    1.77
     directe
    1.77
     directa
    1.59
     directly
    1.47
     directos
    1.45
    Activations Density 0.068%

    No Known Activations