© 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. 3946
    Prev
    Next
    INDEX
    Explanations

    elements of scientific methodology and experimental design

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

    followed by "to [verb]"

    np_acts-logits-general · gemini-2.0-flash

    to investigate or determine

    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
     >=",
    -0.76
     يتيمه
    -0.65
    IndentedString
    -0.55
    ագրություններ
    -0.54
    ̍t
    -0.54
    Referencie
    -0.53
    Consejos
    -0.52
    Xna
    -0.52
    claimers
    -0.52
    hoben
    -0.52
    POSITIVE LOGITS
     determine
    1.26
     determining
    1.22
     ascertaining
    1.18
     checking
    1.08
     ascertain
    1.08
    determine
    1.07
    Determine
    1.07
     determines
    1.06
     Determine
    1.02
     Determining
    1.00
    Activations Density 0.715%

    No Known Activations