© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 3-GEMMASCOPE-RES-16K
    11. 16044
    Prev
    Next
    INDEX
    Explanations

    advertisement-related content, particularly promotional phrases

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ModelExpression
    -0.91
     Audiodateien
    -0.76
    kháu
    -0.76
    contentLoaded
    -0.74
    InSection
    -0.71
    XmlAccessorType
    -0.70
    httphttps
    -0.70
     وتسجيلات
    -0.68
    ConstraintMaker
    -0.67
    malink
    -0.66
    POSITIVE LOGITS
    <eos>
    0.56
    }/>
    0.46
    WriteTagHelper
    0.45
    Clik
    0.45
    StringProperty
    0.45
    ↵↵
    0.44
    )}_
    0.44
    METAL
    0.41
     gestes
    0.40
    }}/>
    0.40
    Activations Density 0.182%

    No Known Activations