© 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. 8117
    Prev
    Next
    INDEX
    Explanations

    structured programming elements and syntax

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

    Code and programming-related terms

    np_acts-logits-general · gemini-2.0-flash

    code definitions and descriptions

    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
     Anſ
    -1.14
     CHAPITRE
    -1.12
     RIPRODUZIONE
    -1.12
     ainfi
    -1.11
     Diſ
    -1.10
     Houſe
    -1.09
     purpoſe
    -1.08
     Monfieur
    -1.07
     Reſ
    -1.07
     Perſ
    -1.05
    POSITIVE LOGITS
    lista
    0.45
     Er
    0.44
    --
    0.44
    inha
    0.44
    titu
    0.41
     Ver
    0.41
     fer
    0.39
    estre
    0.39
    rxjs
    0.39
     Des
    0.39
    Activations Density 0.120%

    No Known Activations