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. 15-GEMMASCOPE-RES-16K
    6. 2889
    Prev
    Next
    INDEX
    Explanations

    phrases indicating the planning and evaluation of community interventions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_15/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     FetchType
    -0.78
    batore
    -0.63
    WaitGroup
    -0.59
     getItemId
    -0.55
    #+#
    -0.54
     JAXBElement
    -0.53
    WebVitals
    -0.53
    GOTREF
    -0.52
    Bước
    -0.52
     [*]
    -0.52
    POSITIVE LOGITS
    <thead>
    0.56
    vily
    0.54
    Geplaatst
    0.52
    rogens
    0.48
    寻常
    0.47
    AxisAlignment
    0.46
     CWE
    0.45
    WART
    0.44
    영어
    0.43
    cinnati
    0.43
    Activations Density 0.444%

    No Known Activations