© 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-IT
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 1263
    Prev
    Next
    INDEX
    Explanations

    expressions of humor or light-heartedness

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

    Emojis or smileys

    np_acts-logits-general · gemini-2.0-flash

    emoticons for happiness or playfulness

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91
    Prompts (Dashboard)
    24,576 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
    دانشنامهٔ
    -0.83
    ArgsConstructor
    -0.82
    tagHelperRunner
    -0.76
    Ārējās
    -0.76
    "])
    
    -0.76
    ]")]
    -0.75
     يتيمه
    -0.74
    __':
    
    -0.73
    __":
    
    -0.73
     autorytatywna
    -0.71
    POSITIVE LOGITS
     :)
    0.56
    !
    0.49
     :-)
    0.41
    .
    0.39
     ;)
    0.39
    !!!
    0.38
     lol
    0.38
    :)
    0.37
     !
    0.36
     :))
    0.36
    Activations Density 0.149%

    No Known Activations