Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 16-GEMMASCOPE-RES-16K
    6. 12742
    Prev
    Next
    INDEX
    Explanations

    terms related to enabling and disabling functions or features

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    "Enable" and related forms

    np_acts-logits-general · gemini-2.0-flash

    enabling functionality

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     polaire
    -0.72
    AndEndTag
    -0.70
    chloro
    -0.68
     كومونز
    -0.65
     fjor
    -0.65
    RunAsync
    -0.64
    bcrypt
    -0.64
     gitti
    -0.64
     suyo
    -0.63
     Leone
    -0.61
    POSITIVE LOGITS
     ENABLE
    1.04
    abling
    1.01
     OnEnable
    1.00
     Enables
    0.99
     Ena
    0.99
     enable
    0.96
    abler
    0.95
     Enable
    0.94
    ENABLE
    0.94
    addPreferredGap
    0.93
    Activations Density 0.076%

    No Known Activations