© 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
    2. Joseph Bloom · Initial Gemma-2B SAEs
    3. Gemma-2B
    4. Residual Stream
    5. 6-RES-JB
    6. 6437
    Prev
    Next
    INDEX
    Explanations

    sequences of characters that resemble German words, like "Drechsler" and "Kaushl", pairing with last names like Schnabl and Bardhy respectively

    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
    703
    +0.14
    0.6%
    1077
    +0.12
    0.5%
    490
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1343
    +0.14
    0.11
    1614
    +0.12
    0.07
    1363
    +0.11
    0.06
    Negative Logits
    <bos>
    -1.03
    ,
    -0.80
    .
    -0.80
    :
    -0.78
     in
    -0.77
    -
    -0.74
     (
    -0.73
     play
    -0.70
    </h2>
    -0.70
     claim
    -0.70
    POSITIVE LOGITS
     embodi
    1.94
     dises
    1.92
     tremb
    1.80
     maneu
    1.75
     squa
    1.75
     thut
    1.71
     increa
    1.71
     erad
    1.69
     mef
    1.68
     aen
    1.66
    Activations Density 0.816%

    No Known Activations