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. 14103
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to consideration or accounting for various factors in decision-making contexts

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

    "into account"

    np_acts-logits-general · gemini-2.0-flash

    into account or consideration

    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
     @"/
    -0.70
    таратура
    -0.62
    StoryboardSegue
    -0.60
    Hozzáférés
    -0.56
     Pera
    -0.54
     defaultstate
    -0.54
    qiang
    -0.53
    firi
    -0.53
    Зноскі
    -0.53
    __(/*!
    -0.52
    POSITIVE LOGITS
     account
    0.91
    account
    0.65
     Account
    0.59
     cuenta
    0.56
    Account
    0.53
    HandlerContext
    0.53
     consideration
    0.53
    ंदीखरीदारी
    0.52
    PerformLayout
    0.52
    AccessFile
    0.52
    Activations Density 0.166%

    No Known Activations