© 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. 24-GEMMASCOPE-RES-16K
    11. 4901
    Prev
    Next
    INDEX
    Explanations

    the word "straight" in various contexts and forms

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

    "Straight" followed by direction-related words

    np_acts-logits-general · gemini-2.0-flash

    straight forward or direct

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    awaiter
    -0.59
    abestanden
    -0.58
    tagHelperRunner
    -0.57
    IElement
    -0.57
    obium
    -0.56
    MessageOf
    -0.54
    __;
    -0.54
     ApiException
    -0.53
    :✨
    -0.53
    URBANA
    -0.53
    POSITIVE LOGITS
    forward
    1.02
    jacket
    0.91
    DeleteBehavior
    0.81
    jacke
    0.81
    eners
    0.80
    FORWARD
    0.77
    laced
    0.76
     otomatig
    0.74
    ening
    0.71
    ener
    0.68
    Activations Density 0.093%

    No Known Activations