© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 4-GEMMASCOPE-RES-16K
    11. 3663
    Prev
    Next
    INDEX
    Explanations

    verbs indicating actions and experiences, particularly in a personal or historical context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 4-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_4/width_16k/average_l0_124
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.hook_resid_post
    Hook Layer
    4
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ſelves
    -0.68
     يتيمه
    -0.58
    kpop
    -0.56
    "}"
    -0.55
     Mult
    -0.54
     houſe
    -0.54
    __))
    -0.53
    ृत
    -0.53
    ("#{
    -0.53
    τέλε
    -0.53
    POSITIVE LOGITS
     himself
    1.40
     his
    1.32
     him
    1.16
    himself
    1.07
     His
    1.05
     He
    1.05
    His
    0.98
     Himself
    0.97
     he
    0.91
    的他
    0.91
    Activations Density 0.711%

    No Known Activations