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. 22-GEMMASCOPE-RES-16K
    6. 11214
    Prev
    Next
    INDEX
    Explanations

    references to materials and adhesives used in crafting or DIY projects

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

    Follows prepositions like "with", "of", or "using"

    np_acts-logits-general · gemini-2.0-flash

    using tape, plastic, or paper

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    AutoScaleMode
    -0.69
    findpost
    -0.66
     Roskov
    -0.65
    UnsafeEnabled
    -0.63
     /*#__
    -0.62
    SpringBootTest
    -0.62
    fromnode
    -0.60
    RegistryLite
    -0.59
    InvalidProtocol
    -0.58
    ExtendWith
    -0.57
    POSITIVE LOGITS
     popsic
    0.74
     plastic
    0.72
     cardboard
    0.72
     old
    0.67
     dow
    0.66
     masking
    0.66
     string
    0.65
     paper
    0.64
     clothe
    0.63
     scraps
    0.61
    Activations Density 0.225%

    No Known Activations