© 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. 16-GEMMASCOPE-RES-16K
    11. 9347
    Prev
    Next
    INDEX
    Explanations

    aspects and limitations of inventions or methods

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

    Follows "method," "disadvantage," "limitation," etc

    np_acts-logits-general · gemini-2.0-flash

    one/another aspect or limitation

    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
    StoryboardSegue
    -0.63
    MigrationBuilder
    -0.55
    enterOuterAlt
    -0.54
     poveznice
    -0.51
     ragazzi
    -0.49
     بيها
    -0.48
    Lähteet
    -0.48
     semuanya
    -0.48
     fallu
    -0.48
    uesia
    -0.47
    POSITIVE LOGITS
     important
    0.75
     recent
    0.66
     aspect
    0.63
     key
    0.62
     importante
    0.61
    imbawa
    0.60
     early
    0.60
     popular
    0.58
    DebuggerNonUser
    0.58
    重要
    0.58
    Activations Density 0.569%

    No Known Activations