© 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-2-9B
    4. Residual Stream - 16k
    5. 28-GEMMASCOPE-RES-16K
    6. 7765
    Prev
    Next
    INDEX
    Explanations

    the use of the word "as" in various contexts

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

    "As" followed by a word

    np_acts-logits-general · gemini-2.0-flash

    as an opener

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 28-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_28/width_16k/average_l0_119
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.28.hook_resid_post
    Hook Layer
    28
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ktore
    -0.46
    BASEPATH
    -0.42
     säga
    -0.41
    SelectedValue
    -0.40
    Gu
    -0.40
    KURZBESCHREIBUNG
    -0.40
    SpringRunner
    -0.39
    できる
    -0.38
    SequentialGroup
    -0.38
    höhe
    -0.37
    POSITIVE LOGITS
     well
    0.69
     follows
    0.68
     opposed
    0.66
     regards
    0.65
    AS
    0.61
     gevolg
    0.61
     usual
    0.58
    pergillus
    0.55
     Photocase
    0.54
    follows
    0.53
    Activations Density 0.391%

    No Known Activations