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. 16-GEMMASCOPE-RES-16K
    6. 1695
    Prev
    Next
    INDEX
    Explanations

    terms related to data operations and processing commands in an API context

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

    before "request" or "List" in code

    np_acts-logits-general · gemini-2.0-flash

    request preparing or processing

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/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.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    GEBURTSDATUM
    -0.93
    featureID
    -0.76
    UnknownFieldSet
    -0.66
     gainera
    -0.66
     ModelExpression
    -0.65
    حياته
    -0.62
    IUrlHelper
    -0.62
    Jeografia
    -0.59
     CreateTagHelper
    -0.57
    adpleegd
    -0.56
    POSITIVE LOGITS
    extAlignment
    0.58
     therewith
    0.52
    mbggenerated
    0.50
    ритори
    0.47
     telt
    0.46
     IMAP
    0.46
     therefor
    0.45
    jface
    0.45
    ibouti
    0.45
     لينك
    0.45
    Activations Density 0.356%

    No Known Activations