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. 21-GEMMASCOPE-RES-16K
    6. 6810
    Prev
    Next
    INDEX
    Explanations

    instances of the word "assumption" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     tarda
    -0.49
    generator
    -0.47
    ALOG
    -0.45
    }`}>
    -0.45
     encontrarse
    -0.44
    elesaikan
    -0.44
    Tikang
    -0.44
     lagar
    -0.43
     Malte
    -0.43
    ])):
    -0.43
    POSITIVE LOGITS
    RTLD
    0.63
     незавершена
    0.63
    PyExc
    0.61
     TextAlign
    0.61
    igneur
    0.60
    InjectAttribute
    0.60
     îmb
    0.58
    ovací
    0.56
    sproz
    0.56
    inigungs
    0.56
    Activations Density 0.296%

    No Known Activations