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-IT SAEs
    3. Gemma-2B-IT
    4. Residual Stream
    5. 12-RES-JB
    6. 8243
    Prev
    Next
    INDEX
    Explanations

    companies, channels, and their ownership details

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    jbloom/Gemma-2b-IT-Residual-Stream-SAEs/gemma_2b_it_blocks.12.hook_resid_post_16384
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    HuggingFaceFW/fineweb
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    standard
    Context Size
    1,024
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    227
    +0.18
    0.5%
    1842
    +0.12
    0.3%
    198
    +0.11
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    227
    +0.18
    0.07
    198
    +0.12
    0.04
    583
    +0.11
    0.02
    Negative Logits
    ==""){
    -0.63
     shewn
    -0.62
     canst
    -0.61
     didst
    -0.61
     hornblende
    -0.60
     tubercle
    -0.60
     hypotension
    -0.57
     smtplib
    -0.57
     heapq
    -0.56
    edicated
    -0.55
    POSITIVE LOGITS
     subsidiaries
    0.79
     subsidiary
    0.73
     subsidi
    0.64
     flagship
    0.62
     affiliates
    0.57
     ekos
    0.56
     alkoh
    0.55
     optik
    0.55
     foton
    0.55
     Kategor
    0.54
    Activations Density 0.476%

    No Known Activations