© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 7088
    Prev
    Next
    INDEX
    Explanations

    instances of narration or actions involving characters in a sequence

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

    "Go" or "went" followed by "on"

    np_acts-logits-general · gemini-2.0-flash

    go on to

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    contentLoaded
    -0.58
    BufferException
    -0.55
    ں
    -0.51
    cephala
    -0.49
    iprot
    -0.47
     betweenstory
    -0.47
    ariate
    -0.46
    WriteTagHelper
    -0.45
    нути
    -0.44
    bootstrapcdn
    -0.43
    POSITIVE LOGITS
     goes
    1.64
     go
    1.55
     went
    1.53
    goes
    1.49
    go
    1.39
     Goes
    1.38
     gone
    1.34
     GOES
    1.34
    went
    1.29
     Went
    1.29
    Activations Density 0.185%

    No Known Activations