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. 20-GEMMASCOPE-RES-16K
    6. 7318
    Prev
    Next
    INDEX
    Explanations

    references to estimations and modeling in statistical or analytical contexts

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

    Following words like "to," "and," "you," or "so"

    np_acts-logits-general · gemini-2.0-flash

    technical discourse and programming terms

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ]")]
    -1.04
    !’
    -1.03
    tvguidetime
    -0.93
    !')
    -0.93
    !');
    -0.92
    !")
    
    -0.90
    !」
    -0.88
    !';
    -0.88
    !}
    -0.87
     TextInputType
    -0.86
    POSITIVE LOGITS
     IIRC
    1.13
     iirc
    1.03
     inderdaad
    0.86
     probably
    0.84
     your
    0.74
     effectivement
    0.74
    </blockquote>
    0.74
     maybe
    0.74
    ↵↵
    0.74
     you
    0.71
    Activations Density 1.040%

    No Known Activations