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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 12742
    Prev
    Next
    INDEX
    Explanations

    references to attempts, capabilities, and outcomes related to securing loans or assistance

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

    Following "to" or securing something

    np_acts-logits-general · gemini-2.0-flash

    obtainsecureget

    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
    出版年
    -0.63
    mich
    -0.60
    yarnpkg
    -0.56
     déchir
    -0.55
    XmlRootElement
    -0.54
    ziom
    -0.53
    TProtocol
    -0.53
     maux
    -0.53
     saluti
    -0.53
     发表于
    -0.52
    POSITIVE LOGITS
     secured
    1.46
     secure
    1.43
     securing
    1.40
     secures
    1.31
    secured
    1.18
    secure
    1.14
     Secure
    1.13
    Secure
    1.11
     nab
    1.02
     obtain
    0.99
    Activations Density 0.322%

    No Known Activations