© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 28-GEMMASCOPE-RES-16K
    11. 8806
    Prev
    Next
    INDEX
    Explanations

    first-person pronouns and expressions of personal opinions or statements

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

    "I" followed by modal verbs or related words

    np_acts-logits-general · gemini-2.0-flash

    I think, I recommend, I doubt

    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
     resourceCulture
    -0.60
     <<<<<<<<<<<<<<
    -0.57
    AddTagHelper
    -0.54
    Cyfarwyddwr
    -0.52
    MessageTagHelper
    -0.52
    styleType
    -0.52
    脚注の使い方
    -0.51
     հղումներ
    -0.51
     CreateTagHelper
    -0.49
     noDo
    -0.49
    POSITIVE LOGITS
     pretty
    0.47
     recomend
    0.45
     think
    0.44
     doubt
    0.43
     would
    0.42
    shutil
    0.42
     havent
    0.41
     presume
    0.41
    pretty
    0.41
     recommend
    0.40
    Activations Density 0.259%

    No Known Activations