© 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. 18-GEMMASCOPE-RES-16K
    11. 11235
    Prev
    Next
    INDEX
    Explanations

    structure and flow control elements in programming code

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Followed by "case" or "usepackage"

    np_acts-logits-general · gemini-2.0-flash

    case statements

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     متعلقه
    -1.23
    ########.
    -0.99
    TagMode
    -0.97
    #
    -0.96
    Espèce
    -0.92
    fjspx
    -0.92
    ագրություններ
    -0.91
     ujednoznacz
    -0.90
    mybatisplus
    -0.89
     виправивши
    -0.88
    POSITIVE LOGITS
    baomidou
    0.44
     and
    0.41
     
    0.39
     vuoden
    0.38
     että
    0.38
    signup
    0.37
     jotka
    0.36
     vaan
    0.36
    multirow
    0.36
    รม
    0.34
    Activations Density 0.403%

    No Known Activations