© 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. 4010
    Prev
    Next
    INDEX
    Explanations

    expressions related to joining or coming together for a common purpose

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

    "join" or its variations

    np_acts-logits-general · gemini-2.0-flash

    join us or forces

    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
    êque
    -0.53
    izr
    -0.48
     -*-
    -0.48
     enim
    -0.48
     Eiffel
    -0.47
    monies
    -0.47
     gevallen
    -0.46
    Stuff
    -0.46
     oakley
    -0.46
     själva
    -0.45
    POSITIVE LOGITS
     forces
    1.33
     join
    1.23
     joins
    1.22
     Joining
    1.17
     JOIN
    1.15
     Joins
    1.14
     Forces
    1.11
    Joining
    1.11
    forces
    1.10
     joining
    1.09
    Activations Density 0.067%

    No Known Activations