© 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. 10332
    Prev
    Next
    INDEX
    Explanations

    the presence of terms related to adherence and adhesion 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 @ 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
    #+#
    -0.90
    complexContent
    -0.89
    findpost
    -0.85
    bootstrapcdn
    -0.81
    OGND
    -0.78
    تقاوى
    -0.77
    SourceChecksum
    -0.73
    styleType
    -0.72
     Erden
    -0.72
     MFC
    -0.72
    POSITIVE LOGITS
    ad
    2.95
    AD
    2.80
     AD
    2.51
     Ad
    2.34
    Ad
    2.23
     ad
    2.21
    ads
    2.01
    ADS
    1.60
    adh
    1.44
     ads
    1.43
    Activations Density 0.125%

    No Known Activations