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. 240
    Prev
    Next
    INDEX
    Explanations

    text related to scientific research, funding, and the academic process

    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
    1042
    +0.14
    0.4%
    2034
    +0.14
    0.4%
    382
    +0.12
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1265
    +0.14
    0.04
    382
    +0.14
    0.04
    2005
    +0.12
    0.03
    Negative Logits
     praktik
    -1.14
     sappi
    -1.12
     solidar
    -1.11
     ristor
    -1.10
     ordina
    -1.07
     ideolog
    -1.06
     Nö
    -1.05
     utop
    -1.05
     stili
    -1.05
     kosme
    -1.04
    POSITIVE LOGITS
     it
    0.84
     there
    0.78
     we
    0.76
     they
    0.70
     perhaps
    0.67
     this
    0.67
     whither
    0.64
     maybe
    0.63
     you
    0.62
    จึง
    0.62
    Activations Density 0.206%

    No Known Activations