© 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. 11-GEMMASCOPE-RES-16K
    6. 1557
    Prev
    Next
    INDEX
    Explanations

    terms related to evaluations and assessments in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 11-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_11/width_16k/average_l0_80
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Hook Layer
    11
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ویکی‌پدیا
    -0.79
     Normdatei
    -0.66
    MimeType
    -0.65
     itſelf
    -0.65
    못
    -0.61
     isKindOfClass
    -0.61
    AccessException
    -0.60
    pins
    -0.59
    interna
    -0.57
    })));
    -0.56
    POSITIVE LOGITS
     themselves
    1.41
    Their
    1.26
     Their
    1.24
     their
    1.24
    themselves
    1.16
     THEIR
    1.11
     they
    1.02
    their
    1.01
     They
    0.96
    They
    0.91
    Activations Density 0.333%

    No Known Activations