Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 16-GEMMASCOPE-RES-16K
    6. 15760
    Prev
    Next
    INDEX
    Explanations

    sections where there are no relevant words or information

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

    Following a question marker

    np_acts-logits-general · gemini-2.0-flash

    original preserve

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     nakalista
    -1.15
     GetEnumerator
    -0.96
     مشين
    -0.91
    DebuggerNonUser
    -0.86
    addPreferredGap
    -0.84
    Hozzáférés
    -0.83
     noqa
    -0.82
    تقاوى
    -0.81
    NameInMap
    -0.80
    ArgsConstructor
    -0.80
    POSITIVE LOGITS
     Wayback
    0.67
     original
    0.58
     оригіналу
    0.51
     Original
    0.50
     Originals
    0.48
     originais
    0.47
     preserve
    0.47
    Original
    0.46
     bãi
    0.46
    thold
    0.46
    Activations Density 0.026%

    No Known Activations