© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 5-GEMMASCOPE-RES-16K
    6. 8467
    Prev
    Next
    INDEX
    Explanations

    location phrases or contextual cues referring to time and space

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.5.hook_resid_post
    Hook Layer
    5
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     hossz
    -0.69
    Abp
    -0.56
    mayr
    -0.56
     Roderick
    -0.55
     huéspedes
    -0.54
     disulfide
    -0.54
    مؤ
    -0.53
    Abitanti
    -0.53
    feuer
    -0.53
    RIQUE
    -0.52
    POSITIVE LOGITS
     consider
    0.91
    ссмо
    0.90
    IUrlHelper
    0.89
     VIEW
    0.88
    Examine
    0.87
     utafitiHapana
    0.85
     regarde
    0.84
    Viewing
    0.83
    consider
    0.82
     Viewing
    0.82
    Activations Density 0.073%

    No Known Activations