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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 4981
    Prev
    Next
    INDEX
    Explanations

    names of people mentioned in the text

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

    Names, followed by a last name or other identifier

    np_acts-logits-general · gemini-2.0-flash

    names followed by last names

    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
    ]")]
    -0.80
    VersionUID
    -0.68
     يتيمه
    -0.64
    SharedCtor
    -0.60
    MENAFN
    -0.59
    SerializedName
    -0.59
    InjectAttribute
    -0.58
    Cyfeiriadau
    -0.57
     indiví
    -0.55
    withIdentifier
    -0.55
    POSITIVE LOGITS
     &
    0.52
     thanks
    0.51
     from
    0.48
    ’
    0.48
    @
    0.48
     loves
    0.47
     likes
    0.47
    Dzięki
    0.46
     thank
    0.46
     bought
    0.43
    Activations Density 0.206%

    No Known Activations