© 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. 5722
    Prev
    Next
    INDEX
    Explanations

    sequences of characters or patterns that include the letter 'z'

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

    Tokens starting with "z"

    np_acts-logits-general · gemini-2.0-flash

    zhao, calizo, et al. citations

    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
     Approach
    -0.81
     approach
    -0.79
     approached
    -0.77
     approaches
    -0.76
     APPROACH
    -0.75
    approach
    -0.73
    y
    -0.70
    Approach
    -0.69
     فريبيس
    -0.68
    رشف
    -0.65
    POSITIVE LOGITS
    s
    0.59
    AddTagHelper
    0.54
    ⿸
    0.51
    pz
    0.49
    c
    0.49
    rw
    0.49
    verwijspagina
    0.48
    ELTS
    0.47
    ska
    0.47
    ✭✭
    0.47
    Activations Density 0.187%

    No Known Activations