© 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. 4050
    Prev
    Next
    INDEX
    Explanations

    conclusive statements and references to findings or proposals in a text

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

    "We" as the first word of a statement

    np_acts-logits-general · gemini-2.0-flash

    We have followed by verb

    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
     later
    -0.84
     Later
    -0.73
    Later
    -0.70
     successivo
    -0.70
    later
    -0.69
     soon
    -0.64
     subsequently
    -0.58
     subsequent
    -0.56
     позже
    -0.54
     später
    -0.53
    POSITIVE LOGITS
    いかがでしたか
    0.89
    いかが
    0.87
    いかがでしょうか
    0.81
    évaluateur
    0.79
    ParallelGroup
    0.78
     tadi
    0.75
    ここまで
    0.73
    MemoryWarning
    0.72
    Hopefully
    0.72
     Hopefully
    0.71
    Activations Density 0.304%

    No Known Activations