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. 6-GEMMASCOPE-RES-16K
    6. 245
    Prev
    Next
    INDEX
    Explanations

    phrases related to the presence or absence of specific qualities or items

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 6-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_6/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.6.hook_resid_post
    Hook Layer
    6
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Julien
    -0.69
     rehearing
    -0.69
    jetunion
    -0.66
    Peptide
    -0.65
     steeper
    -0.65
     nadie
    -0.65
     jazdy
    -0.64
     Мексичка
    -0.63
     flats
    -0.63
     Kart
    -0.63
    POSITIVE LOGITS
     presence
    2.45
    presence
    2.21
     Presence
    2.16
    Presence
    2.08
     présence
    1.99
     presencia
    1.74
     presença
    1.63
     presenza
    1.58
     присут
    1.53
     PRES
    1.46
    Activations Density 0.148%

    No Known Activations