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. 6-RES-JB
    6. 9201
    Prev
    Next
    INDEX
    Explanations

    information about guidelines or rules regarding home and pet care

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    jbloom/Gemma-2b-Residual-Stream-SAEs/gemma_2b_blocks.6.hook_resid_post_16384_anthropic_fast_lr
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    HuggingFaceFW/fineweb
    Features
    16,384
    Data Type
    torch.float32
    Hook Point
    blocks.6.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    HuggingFaceFW/fineweb
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    1482
    +0.09
    0.2%
    1491
    +0.07
    0.2%
    609
    +0.07
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1040
    +0.09
    0.03
    1003
    +0.07
    0.03
    1423
    +0.07
    0.03
    Negative Logits
    Saluti
    -0.68
     loath
    -0.65
     inconce
    -0.62
     Homem
    -0.61
    Molto
    -0.57
     sombr
    -0.57
     indescri
    -0.57
     Ediciones
    -0.55
     churrasco
    -0.55
     Agreg
    -0.54
    POSITIVE LOGITS
     Magaz
    0.72
     poveznice
    0.71
    Sklici
    0.67
     Freuden
    0.66
    évalu
    0.63
     Sted
    0.63
     Heere
    0.63
     Oester
    0.63
     autorytatywna
    0.62
    IntoConstraints
    0.59
    Activations Density 0.017%

    No Known Activations