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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 17-GEMMASCOPE-RES-16K
    6. 5899
    Prev
    Next
    INDEX
    Explanations

    representations of code and data structures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 17-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_17/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.17.hook_resid_post
    Hook Layer
    17
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    InvalidProtocol
    -0.50
    TestBed
    -0.47
    HomeAsUp
    -0.46
    Obrázky
    -0.46
     penggemar
    -0.45
    Photographer
    -0.44
    erste
    -0.43
     melaksanakan
    -0.43
     numerically
    -0.43
    Upgrades
    -0.42
    POSITIVE LOGITS
     enrich
    0.76
    Personendaten
    0.74
    ArgsConstructor
    0.63
     enri
    0.63
     extracted
    0.63
     corpus
    0.62
     Gutenberg
    0.62
     content
    0.62
     sentence
    0.61
    Corpus
    0.61
    Activations Density 0.461%

    No Known Activations