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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 65k
    5. 13-GEMMASCOPE-RES-65K
    6. 15040
    Prev
    Next
    INDEX
    Explanations

    nested structures and braces in code

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 13-gemmascope-res-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_13/width_65k/average_l0_75
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    Data Type
    float32
    Hook Name
    blocks.13.hook_resid_post
    Hook Layer
    13
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    enterOuterAlt
    -0.60
     EdgeInsets
    -0.55
    multer
    -0.55
    posedge
    -0.54
    mybatisplus
    -0.54
    AndEndTag
    -0.52
    MigrationBuilder
    -0.52
     Mattress
    -0.52
     done
    -0.50
    Gdx
    -0.48
    POSITIVE LOGITS
    expandindo
    1.01
     виправивши
    0.88
     дописавши
    0.65
    IUrlHelper
    0.60
     luto
    0.58
     nahilalakip
    0.57
    onAttach
    0.57
    principalTable
    0.56
    %)$
    0.56
     InputDecoration
    0.54
    Activations Density 0.010%

    No Known Activations