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. 2-GEMMASCOPE-RES-16K
    6. 15934
    Prev
    Next
    INDEX
    Explanations

    repeated sequences of characters or symbols, often indicating formatting or structural elements in code

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_2/width_16k/average_l0_141
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    WaitGroup
    -0.65
    OrBuilder
    -0.64
     Trouvez
    -0.59
    іє
    -0.56
    bobox
    -0.56
    IsMutable
    -0.53
    verwijspagina
    -0.53
    waits
    -0.53
    __':
    -0.52
    PreAuthorize
    -0.52
    POSITIVE LOGITS
     '../../../../
    1.01
     '../../
    0.98
     '../../../
    0.93
     "../../../
    0.87
     "../../
    0.86
    setState
    0.85
     "../../../../
    0.74
    ////////////////
    0.69
    ('../../../
    0.69
    ('../../
    0.68
    Activations Density 0.062%

    No Known Activations