© 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. 14-GEMMASCOPE-RES-16K
    11. 4558
    Prev
    Next
    INDEX
    Explanations

    references to game-related activities and events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 14-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_14/width_16k/average_l0_84
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.14.hook_resid_post
    Hook Layer
    14
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     CURIAM
    -0.70
     nakalista
    -0.56
    gridx
    -0.53
    PYX
    -0.53
    expandindo
    -0.52
    Enllaces
    -0.52
     disambiguazione
    -0.51
     validamos
    -0.51
    ❋
    -0.50
    nikon
    -0.50
    POSITIVE LOGITS
     preparation
    1.16
     Preparation
    1.11
    preparation
    1.02
     preparations
    1.02
     PREPARATION
    1.01
    Preparation
    0.99
     prep
    0.96
     prepping
    0.93
     Preparations
    0.92
     preparing
    0.92
    Activations Density 0.294%

    No Known Activations