© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 24-GEMMASCOPE-RES-16K
    6. 6383
    Prev
    Next
    INDEX
    Explanations

    affirmative statements or confirmations of identity and experience

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

    Follows conversational confirmations/agreements

    np_acts-logits-general · gemini-2.0-flash

    affirmations and negations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_24/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     allgemein
    -0.36
    principalColumn
    -0.36
     anyway
    -0.35
     pulseras
    -0.34
     faudrait
    -0.33
     físicas
    -0.33
    PhysRevLett
    -0.32
     andererseits
    -0.32
     generale
    -0.32
     fís
    -0.31
    POSITIVE LOGITS
     EconPapers
    0.75
    󠁮
    0.66
    
    0.63
     مرئيه
    0.61
    :✨
    0.59
    OGND
    0.56
    HasColumnType
    0.54
    ucker
    0.54
     nahilalakip
    0.54
    #+#
    0.53
    Activations Density 0.284%

    No Known Activations