© 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. 9-GEMMASCOPE-RES-16K
    6. 7720
    Prev
    Next
    INDEX
    Explanations

    terms related to technology and computing

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_9/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     الحره
    -0.61
    )”.
    -0.61
     ?";
    -0.59
    Varint
    -0.59
     XNUMX
    -0.58
    momix
    -0.58
     photolibrary
    -0.58
    .”)
    -0.57
    ?')
    -0.57
     Kond
    -0.57
    POSITIVE LOGITS
     TextInputType
    0.75
     propOrder
    0.67
     &___
    0.63
    DeleteBehavior
    0.59
    EndInit
    0.58
    protoimpl
    0.58
    XmlEnum
    0.54
    पया
    0.54
    ftagPool
    0.54
    awtextra
    0.53
    Activations Density 0.076%

    No Known Activations