© 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-2-9B-IT
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 513
    Prev
    Next
    INDEX
    Explanations

    relationships between database tables and their foreign key constraints

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

    Database tables and foreign keys

    np_acts-logits-general · gemini-2.0-flash

    database ids and relations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91
    Prompts (Dashboard)
    24,576 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
    ⤹
    -0.70
     Administrativna
    -0.66
    ThroughAttribute
    -0.64
    出版年
    -0.63
     विश्वसनीयता
    -0.63
     OMITBAD
    -0.63
    MessageOf
    -0.63
    UnusedPrivate
    -0.62
    Personendaten
    -0.60
    SequentialGroup
    -0.60
    POSITIVE LOGITS
    ManyToOne
    0.36
     bridge
    0.34
    eqref
    0.32
     Bridge
    0.30
     car
    0.30
     termin
    0.30
     lain
    0.29
     theme
    0.29
     Lord
    0.28
     family
    0.28
    Activations Density 0.177%

    No Known Activations