© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Initial Gemma-2B SAEs
    5. Gemma-2B
    7. Residual Stream
    9. 6-RES-JB
    11. 280
    Prev
    Next
    INDEX
    Explanations

    names of individuals or organizations

    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
    395
    +0.16
    0.7%
    1124
    +0.16
    0.7%
    1926
    +0.13
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    395
    +0.16
    0.04
    1056
    +0.16
    0.05
    227
    +0.13
    0.05
    Negative Logits
    <bos>
    -1.78
    guang
    -1.37
    xiu
    -1.35
    qiao
    -1.25
    anyuan
    -1.21
    qian
    -1.17
    huo
    -1.11
     Xiu
    -1.09
    xun
    -1.06
    zheng
    -1.04
    POSITIVE LOGITS
     Strukt
    0.87
     alkoh
    0.87
     Lins
    0.86
     quoique
    0.83
     Abbé
    0.79
     Heeren
    0.79
     kosme
    0.76
     kompati
    0.75
     geograf
    0.75
    rcParams
    0.75
    Activations Density 0.244%

    No Known Activations