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. 4-GEMMASCOPE-RES-16K
    6. 16026
    Prev
    Next
    INDEX
    Explanations

    phrases related to scientific validation or confirmation

    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
     
    -0.52
    ️
    -0.51
     stimm
    -0.51
     #
    -0.45
     +
    -0.44
     r
    -0.43
     F
    -0.43
     aka
    -0.43
     w
    -0.43
     NYC
    -0.43
    POSITIVE LOGITS
     snippetHide
    1.03
    GEBURTSDATUM
    0.95
     كومونز
    0.86
    AndEndTag
    0.84
    ArgsConstructor
    0.81
    SourceChecksum
    0.79
     Efq
    0.73
     iſt
    0.71
     fhort
    0.71
    GraphicsUnit
    0.70
    Activations Density 0.238%

    No Known Activations