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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 6310
    Prev
    Next
    INDEX
    Explanations

    text related to legal terms and copyright notices

    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
    50
    +0.15
    0.6%
    1310
    +0.09
    0.4%
    1994
    +0.09
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1948
    +0.15
    0.04
    235
    +0.09
    0.04
    1811
    +0.09
    0.02
    Negative Logits
    <bos>
    -2.02
    ⓧ
    -0.68
    #![
    -0.68
    
    
    -0.67
    OneToMany
    -0.64
    بعض
    -0.64
    ↘
    -0.62
     lombok
    -0.60
    Тай
    -0.59
     don
    -0.59
    POSITIVE LOGITS
     ftu
    1.47
     lele
    1.43
     sergio
    1.39
     riviera
    1.38
     jorge
    1.37
     bandung
    1.37
     milano
    1.37
     fays
    1.36
     javier
    1.35
     ftre
    1.34
    Activations Density 0.825%

    No Known Activations