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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 787
    Prev
    Next
    INDEX
    Explanations

    snippets of code related to API request handling

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

    Code or markup language fragments

    np_acts-logits-general · gemini-2.0-flash

    following code blocks

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 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
     "..\..\..\
    -0.57
    ViewChild
    -0.54
    NameInMap
    -0.52
    migrationBuilder
    -0.51
    abestanden
    -0.51
    таратура
    -0.50
     fre
    -0.50
    BagLayout
    -0.50
    jgl
    -0.50
     HasFactory
    -0.49
    POSITIVE LOGITS
     zelve
    0.71
     judiciales
    0.67
     Mercier
    0.66
     InputDecoration
    0.65
     industriales
    0.65
    omiast
    0.64
     ainfi
    0.64
    ]},
    0.60
    Anmerkungen
    0.59
     producteurs
    0.58
    Activations Density 0.055%

    No Known Activations