Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 24-GEMMASCOPE-RES-16K
    6. 8104
    Prev
    Next
    INDEX
    Explanations

    aspects related to vehicle features and specifications

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

    Peugeot cars and SUVs

    np_acts-logits-general · gemini-2.0-flash

    new car models

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 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
     Roskov
    -0.82
    SequentialGroup
    -0.67
     дописавши
    -0.65
    BeginContext
    -0.64
     препратки
    -0.64
     חיצוניים
    -0.61
    IntoConstraints
    -0.60
     صوتيه
    -0.59
     saites
    -0.58
    forName
    -0.57
    POSITIVE LOGITS
     Vauxhall
    0.65
     Vaux
    0.62
     petrol
    0.53
     £
    0.53
     hefyd
    0.52
    OGND
    0.52
     authorised
    0.52
     motorway
    0.49
     Bonnet
    0.49
     Clio
    0.48
    Activations Density 0.185%

    No Known Activations