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. 3-GEMMASCOPE-RES-16K
    6. 12507
    Prev
    Next
    INDEX
    Explanations

    words related to the concept of life and its dynamics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     فريبيس
    -0.67
     المعيارى
    -0.66
    ########.
    -0.66
     EnglishChoose
    -0.61
     Marten
    -0.57
    DropTable
    -0.55
    timately
    -0.54
    MENAFN
    -0.53
    hmac
    -0.53
     Jaeger
    -0.53
    POSITIVE LOGITS
    Демографія
    0.68
     initComponents
    0.67
    Personensuche
    0.65
    वार
    0.64
     AssemblyCulture
    0.58
    }();
    0.57
    脚注の使い方
    0.56
     betreft
    0.56
     blik
    0.53
    Truth
    0.53
    Activations Density 0.256%

    No Known Activations