© 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. 6-GEMMASCOPE-RES-16K
    6. 11980
    Prev
    Next
    INDEX
    Explanations

    instances of the prefix "mis-" indicating errors or inaccuracies

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 6-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_6/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.6.hook_resid_post
    Hook Layer
    6
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    InputBorder
    -0.92
    PropertyChanging
    -0.87
     tramonto
    -0.86
    ContentAsync
    -0.85
     חיצוניים
    -0.85
    horabuena
    -0.84
     LCCN
    -0.83
    RegistryLite
    -0.82
    InjectMocks
    -0.81
     propOrder
    -0.81
    POSITIVE LOGITS
     mis
    2.07
    Mis
    1.84
     Mis
    1.84
    mis
    1.84
     MIS
    1.81
    MIS
    1.55
     misuse
    1.19
     misc
    1.14
     misused
    1.12
     Mish
    1.11
    Activations Density 0.060%

    No Known Activations