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. 22-GEMMASCOPE-RES-16K
    6. 10320
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions and equations related to physical models or concepts

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

    "Substituting", "substitution", or "substitute"

    np_acts-logits-general · gemini-2.0-flash

    finding substitutions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    __(/*!
    -0.77
    انيف
    -0.76
    GraphicsUnit
    -0.66
     CreateTagHelper
    -0.65
    hoeddwyd
    -0.64
    رشف
    -0.63
    OGND
    -0.63
     saites
    -0.62
    SBATCH
    -0.59
    GEBURTSDATUM
    -0.59
    POSITIVE LOGITS
     substituting
    0.97
     substitution
    0.94
     Substitution
    0.84
     Substituting
    0.83
     substitute
    0.83
    subs
    0.79
    substitute
    0.79
     substitutions
    0.77
     substituted
    0.77
    Substituting
    0.77
    Activations Density 1.500%

    No Known Activations