© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 24-GEMMASCOPE-RES-16K
    11. 5670
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "interview" and related terms or variations within the text

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

    "interview" or "HIV"

    np_acts-logits-general · gemini-2.0-flash

    interviews about HIV

    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
     Osorio
    -0.51
    jboss
    -0.48
    getNum
    -0.44
     lot
    -0.43
    друг
    -0.42
    lè
    -0.42
     pops
    -0.41
     state
    -0.41
    getLine
    -0.40
     matter
    -0.39
    POSITIVE LOGITS
    ectady
    0.62
    BASEPATH
    0.60
     endblock
    0.56
    yakarta
    0.55
     inoxidable
    0.53
     HIV
    0.53
     DPRD
    0.52
     Lambeth
    0.52
     Guadalajara
    0.52
    IOException
    0.52
    Activations Density 0.890%

    No Known Activations