© 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. 15-GEMMASCOPE-RES-16K
    6. 1944
    Prev
    Next
    INDEX
    Explanations

    phrases related to advice and guidance across various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_15/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     entro
    -0.59
    \{\\
    -0.56
    HTTPResponse
    -0.54
     ente
    -0.54
     Hamlin
    -0.53
     Metropolis
    -0.53
     المعيارى
    -0.53
    unif
    -0.52
     placent
    -0.52
     Unbe
    -0.51
    POSITIVE LOGITS
     advice
    1.29
     advise
    1.24
     Advice
    1.21
     advisors
    1.20
    advice
    1.19
    Advis
    1.16
    Advice
    1.16
    advis
    1.14
     advisor
    1.13
     advises
    1.11
    Activations Density 0.123%

    No Known Activations