Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 962
    Prev
    Next
    INDEX
    Explanations

    Java import statements, specifically targeting libraries and packages related to Apache Tika and annotations

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

    File extensions used in import statements

    np_acts-logits-general · gemini-2.0-flash

    programming language constructs

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    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
    -0.72
    MessageOf
    -0.67
     utafitiHapana
    -0.66
    InitVars
    -0.63
    omitempty
    -0.63
    RectangleBorder
    -0.61
     виправивши
    -0.60
    ViewFeatures
    -0.60
    InputBorder
    -0.59
    (!__
    -0.58
    POSITIVE LOGITS
     kağıdı
    0.42
    álisis
    0.41
     péné
    0.41
     Internasional
    0.40
     quelquefois
    0.39
     modeling
    0.39
     estudar
    0.39
     saldır
    0.38
     modelling
    0.37
    ondres
    0.37
    Activations Density 0.408%

    No Known Activations