© 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. 18-GEMMASCOPE-RES-16K
    11. 6426
    Prev
    Next
    INDEX
    Explanations

    phrases that emphasize the concept of "all" or totality in various contexts

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

    "all" followed by a determiner

    np_acts-logits-general · gemini-2.0-flash

    all the

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Any
    -0.56
    Anywhere
    -0.56
     Anywhere
    -0.55
     Any
    -0.55
     anywhere
    -0.53
    Lua
    -0.52
    both
    -0.52
     Maggiore
    -0.50
    DebuggerNonUser
    -0.50
     oprot
    -0.48
    POSITIVE LOGITS
     InputDecoration
    0.77
    ieteur
    0.71
     '{@
    0.68
    Personendaten
    0.68
     these
    0.64
     disambiguazione
    0.64
    rungsseite
    0.61
     AttributeSet
    0.60
    OrWhiteSpace
    0.60
     تانيه
    0.60
    Activations Density 0.104%

    No Known Activations