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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 18-GEMMASCOPE-RES-16K
    6. 1732
    Prev
    Next
    INDEX
    Explanations

    references to specific cases or examples in a scientific or literary context

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

    Punctuation followed by conjunctions or modifiers

    np_acts-logits-general · gemini-2.0-flash

    quantities and numbers

    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
     betweenstory
    -0.64
    __*/
    -0.61
    atars
    -0.56
    AndPassword
    -0.55
    ]]);
    -0.54
    mybatisplus
    -0.53
    addWidget
    -0.53
    theless
    -0.52
    ềm
    -0.51
    enumi
    -0.51
    POSITIVE LOGITS
     plupart
    1.74
     mayoría
    1.65
     maioria
    1.60
     meisten
    1.58
     some
    1.48
     kebanyakan
    1.48
     большинство
    1.45
     algunos
    1.45
     meeste
    1.42
     majority
    1.42
    Activations Density 1.199%

    No Known Activations