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. 8296
    Prev
    Next
    INDEX
    Explanations

    terms related to legal or regulatory frameworks and their implementation

    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
    RegressionTest
    -0.72
     جغرافيا
    -0.59
    kloped
    -0.59
    rizona
    -0.58
    انيف
    -0.56
    expandindo
    -0.55
    repar
    -0.54
     predisposition
    -0.54
     &=&
    -0.53
     []);
    -0.52
    POSITIVE LOGITS
     effective
    1.23
    Effective
    1.19
    effective
    1.16
     Effective
    1.14
     EFFECTIVE
    1.01
     effectiveness
    0.96
    生效
    0.92
    ffective
    0.91
    有效
    0.90
     Effectiveness
    0.87
    Activations Density 0.478%

    No Known Activations