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. 13075
    Prev
    Next
    INDEX
    Explanations

    terms related to naming or labeling something

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

    Follows tokens like "called," "dubbed," "named," or "titled"

    np_acts-logits-general · gemini-2.0-flash

    introducing a name or label

    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
     myſelf
    -0.78
     ſche
    -0.76
     Majefty
    -0.75
     juſ
    -0.75
     itſelf
    -0.75
     ſeveral
    -0.73
     raiſ
    -0.71
     poffible
    -0.70
    出版年
    -0.68
     Reſ
    -0.68
    POSITIVE LOGITS
     simply
    1.25
     ‘
    1.22
     '
    1.11
    simply
    0.99
     appunto
    0.99
     “
    0.98
     simplesmente
    0.98
     "
    0.96
     «
    0.95
     semplicemente
    0.92
    Activations Density 0.330%

    No Known Activations