© 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. 5-GEMMASCOPE-RES-16K
    11. 8830
    Prev
    Next
    INDEX
    Explanations

    discussions about belief and assertion, particularly those that challenge common opinions or claims

    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
    uxxxx
    -0.74
     lenker
    -0.70
     Audiodateien
    -0.62
    原始内容存档于
    -0.60
    новништво
    -0.56
    NamedQueries
    -0.55
    WritableDatabase
    -0.52
    ysis
    -0.51
    клопе
    -0.51
     муніципалі
    -0.50
    POSITIVE LOGITS
    bilisi
    0.54
    MIME
    0.54
     Borel
    0.52
    owników
    0.52
    anmoins
    0.51
     kwanza
    0.50
    noinspection
    0.49
    DataContract
    0.49
     Clou
    0.49
     Makefile
    0.49
    Activations Density 0.190%

    No Known Activations