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. 6-GEMMASCOPE-RES-16K
    6. 6243
    Prev
    Next
    INDEX
    Explanations

    references to stairs, staircases, and related spatial concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 6-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_6/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.6.hook_resid_post
    Hook Layer
    6
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     tamu
    -0.58
     fej
    -0.57
     Realm
    -0.54
    去
    -0.53
     realm
    -0.52
     punt
    -0.51
    Роз
    -0.49
    ngilizce
    -0.48
    pointer
    -0.48
    utschein
    -0.47
    POSITIVE LOGITS
     climb
    1.18
     climbs
    1.17
     climber
    1.16
     Stair
    1.13
     Climb
    1.12
     ascent
    1.11
     stairs
    1.10
     climbers
    1.09
     climbing
    1.09
     Climbing
    1.09
    Activations Density 0.347%

    No Known Activations