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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Initial Gemma-2B SAEs
    3. Gemma-2B
    4. Residual Stream
    5. 10-RES-JB
    6. 1160
    Prev
    Next
    INDEX
    Explanations

    scientific terminology related to biology and anatomy

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    jbloom/Gemma-2b-Residual-Stream-SAEs/gemma_2b_blocks.10.hook_resid_post_16384
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    chanind/openwebtext-gemma
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    standard
    Context Size
    1,024
    Dataset
    ctigges/openwebtext-gemma-1024-cl
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    1331
    +0.12
    0.4%
    394
    +0.12
    0.4%
    1967
    +0.12
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1363
    +0.12
    0.06
    394
    +0.12
    0.05
    1343
    +0.12
    0.06
    Negative Logits
    <bos>
    -1.65
    Referencie
    -0.70
    Iné
    -0.69
    suporte
    -0.66
    Zdroj
    -0.65
    mbggenerated
    -0.64
     AssemblyCompany
    -0.63
    WireFormat
    -0.63
    BENEF
    -0.63
    RemoveField
    -0.62
    POSITIVE LOGITS
     fto
    1.55
     fuf
    1.53
     thut
    1.47
     fta
    1.44
     emphat
    1.42
     aen
    1.40
     Augu
    1.38
     ftu
    1.37
     reft
    1.36
     oun
    1.35
    Activations Density 0.212%

    No Known Activations