© 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. 22-GEMMASCOPE-RES-16K
    11. 1643
    Prev
    Next
    INDEX
    Explanations

    key statistics or elements related to financial conditions and recommendations

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

    Prepositions like "among" and tokens after periods

    np_acts-logits-general · gemini-2.0-flash

    amongst

    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
    AddTagHelper
    -0.63
     nargin
    -0.58
    elsif
    -0.55
     nemmeno
    -0.55
    paravant
    -0.55
     kapag
    -0.54
    Neither
    -0.53
     unknownFields
    -0.53
    inguém
    -0.52
    下载附件
    -0.51
    POSITIVE LOGITS
     among
    2.21
     Among
    2.06
    among
    1.99
    Among
    1.95
     amongst
    1.84
     Amongst
    1.75
     AMONG
    1.73
     parmi
    1.51
     antaranya
    1.51
     blant
    1.51
    Activations Density 0.319%

    No Known Activations