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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 11-GEMMASCOPE-RES-16K
    6. 7720
    Prev
    Next
    INDEX
    Explanations

    descriptions of automotive parts and their conditions

    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
    ErrUnexpectedEOF
    -0.63
    LoginComponent
    -0.63
     pter
    -0.63
    });*/
    -0.62
    "}")
    -0.62
    })*/
    -0.59
    dike
    -0.58
    PMailer
    -0.57
    '}),
    -0.56
    '}>
    -0.56
    POSITIVE LOGITS
     aftermarket
    0.75
     upgrades
    0.70
     upgrade
    0.67
     kasarigan
    0.58
     modific
    0.58
     modifi
    0.58
     Sport
    0.58
    Sport
    0.57
     upgraded
    0.57
     kit
    0.55
    Activations Density 0.130%

    No Known Activations