© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 5-GEMMASCOPE-RES-16K
    6. 10772
    Prev
    Next
    INDEX
    Explanations

    individuals and their roles or contributions in interviews and discussions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.5.hook_resid_post
    Hook Layer
    5
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    bootstrapcdn
    -0.72
    HomeAsUpEnabled
    -0.56
     Meksiku
    -0.56
     ſtre
    -0.55
     ſen
    -0.54
     ſub
    -0.53
    equila
    -0.53
    клопе
    -0.52
    withIdentifier
    -0.52
    ITHUB
    -0.51
    POSITIVE LOGITS
     Administrativna
    0.70
    XmlAccessType
    0.62
    зулта
    0.57
    bewerken
    0.55
    RepeatedField
    0.54
    MockBean
    0.54
     numerus
    0.52
    IContainer
    0.49
     excru
    0.46
    存于互联网档案馆
    0.46
    Activations Density 0.076%

    No Known Activations