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. 24-GEMMASCOPE-RES-16K
    6. 8070
    Prev
    Next
    INDEX
    Explanations

    terms and phrases related to eCommerce platforms and their features

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

    "[Something] solution" or "[Something] product"

    np_acts-logits-general · gemini-2.0-flash

    software product or solution

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    újo
    -0.65
    BagConstraints
    -0.58
    Previews
    -0.56
    TagMode
    -0.56
    ---*/
    -0.52
    adors
    -0.52
    AxisAlignment
    -0.51
    下载附件
    -0.51
    DataURL
    -0.49
    dataclass
    -0.49
    POSITIVE LOGITS
     running
    1.01
     deployed
    0.98
     leveraging
    0.94
     powering
    0.94
     built
    0.90
     powered
    0.87
    running
    0.84
     archite
    0.84
     developed
    0.78
    built
    0.78
    Activations Density 0.403%

    No Known Activations