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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 22-GEMMASCOPE-RES-16K
    11. 9181
    Prev
    Next
    INDEX
    Explanations

    function definitions and related syntax elements in code

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

    Code snippets or code-related syntax

    np_acts-logits-general · gemini-2.0-flash

    code delimiters

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    wpi
    -0.60
    atimes
    -0.53
     pesos
    -0.48
    HostException
    -0.48
     Bik
    -0.47
     carri
    -0.47
    lüğ
    -0.46
     déf
    -0.46
    skri
    -0.46
    URLException
    -0.46
    POSITIVE LOGITS
    IUrlHelper
    0.63
    KommentareTeilen
    0.60
    íncia
    0.58
     console
    0.57
    URIComponent
    0.53
    enderror
    0.53
    Παραπομπές
    0.53
    BeginInit
    0.52
     déput
    0.52
    encodeWith
    0.51
    Activations Density 0.042%

    No Known Activations