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. 17-GEMMASCOPE-RES-16K
    6. 1218
    Prev
    Next
    INDEX
    Explanations

    words indicating refusal or negation in decision-making contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 17-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_17/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.17.hook_resid_post
    Hook Layer
    17
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     pinulongan
    -0.60
    GenerationType
    -0.57
    iecie
    -0.56
     zd
    -0.53
    soort
    -0.53
     Drapeau
    -0.52
    τρο
    -0.51
    leep
    -0.51
     focal
    -0.50
     Pin
    -0.50
    POSITIVE LOGITS
     melakukannya
    0.76
    devamını
    0.65
     fernández
    0.61
     aikaa
    0.60
    这样做
    0.59
     partecipare
    0.59
     solches
    0.58
     tričko
    0.58
     eccell
    0.58
     concernés
    0.58
    Activations Density 0.421%

    No Known Activations