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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlogSlackPrivacy & 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. 20-GEMMASCOPE-RES-16K
    6. 6733
    Prev
    Next
    INDEX
    Explanations

    annotations and configurations in a programming context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    XmlAttribute
    -0.46
     στιγ
    -0.45
    staticmethod
    -0.44
     var
    -0.44
     never
    -0.44
    XmlElement
    -0.44
     incident
    -0.43
    loff
    -0.42
    SerializeField
    -0.41
    PathVariable
    -0.41
    POSITIVE LOGITS
    XmlAccessorType
    0.86
    httphttps
    0.84
    ANNES
    0.80
    Slf
    0.79
    tagHelperRunner
    0.78
    styleType
    0.78
     tartalomajánló
    0.77
     дописавши
    0.77
    SpringBootTest
    0.76
    
    0.75
    Activations Density 0.029%

    No Known Activations