© 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. 2-GEMMASCOPE-RES-16K
    11. 8741
    Prev
    Next
    INDEX
    Explanations

    instances of the word "pull" in various contexts, indicating a focus on actions related to pulling or bringing together

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_2/width_16k/average_l0_141
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     nahilalakip
    -0.86
    Abp
    -0.74
    ymce
    -0.66
    temi
    -0.61
    protoimpl
    -0.58
     postIndex
    -0.58
    XmlAccessorType
    -0.58
    BeforeClass
    -0.57
     HasFactory
    -0.55
     Heiden
    -0.55
    POSITIVE LOGITS
     pull
    4.05
     Pull
    3.78
    pull
    3.76
    Pull
    3.65
     PULL
    3.61
     pulled
    3.53
     pulls
    3.51
     pulling
    3.48
     Pulling
    3.24
    PULL
    3.20
    Activations Density 0.045%

    No Known Activations