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. 12-GEMMASCOPE-RES-16K
    6. 2707
    Prev
    Next
    INDEX
    Explanations

    phrases indicating obligations or expectations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    исленность
    -0.68
    jstor
    -0.66
     Walkover
    -0.66
    ukone
    -0.65
    MemoryWarning
    -0.65
    isticated
    -0.64
     незавершена
    -0.61
    raits
    -0.61
    ingly
    -0.60
    Personendaten
    -0.60
    POSITIVE LOGITS
     be
    0.70
     StringField
    0.59
     CreateTagHelper
    0.55
     bear
    0.54
    gatsby
    0.53
    /*:
    0.53
     do
    0.53
     go
    0.53
    be
    0.53
     hide
    0.52
    Activations Density 0.167%

    No Known Activations