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. 5-GEMMASCOPE-RES-16K
    6. 10008
    Prev
    Next
    INDEX
    Explanations

    cryptographic hash functions and their properties

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.5.hook_resid_post
    Hook Layer
    5
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     themſelves
    -0.70
     myſelf
    -0.64
     Priv
    -0.64
     chofe
    -0.63
     reaſon
    -0.60
     becauſe
    -0.60
    chymal
    -0.60
    ſelves
    -0.59
     yourselves
    -0.58
     maneuver
    -0.58
    POSITIVE LOGITS
     hashlib
    1.14
    MessageDigest
    0.89
     hashCode
    0.79
     hash
    0.76
    NoSuchAlgorithm
    0.73
     OFDb
    0.73
     Hash
    0.71
    Hash
    0.67
     hashes
    0.66
    SourceChecksum
    0.65
    Activations Density 0.250%

    No Known Activations