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. 4-GEMMASCOPE-RES-16K
    6. 15859
    Prev
    Next
    INDEX
    Explanations

    words related to locations or surfaces involved in physical activities or events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 4-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_4/width_16k/average_l0_124
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.hook_resid_post
    Hook Layer
    4
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ModelAdmin
    -0.68
     C
    -0.47
    principalColumn
    -0.46
    Datuak
    -0.46
    ilar
    -0.46
     c
    -0.45
     Che
    -0.45
     Chi
    -0.45
    ACHED
    -0.44
    tipation
    -0.44
    POSITIVE LOGITS
    AndEndTag
    0.87
    ✨:
    0.86
     streets
    0.85
     houſe
    0.77
     pavement
    0.77
    AddTagHelper
    0.74
     floor
    0.73
     Streets
    0.72
     sidewalk
    0.72
     pavements
    0.71
    Activations Density 0.394%

    No Known Activations