© 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. 0-RES-JB
    11. 458
    Prev
    Next
    INDEX
    Explanations

    proper names

    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.0.hook_resid_post_16384_anthropic
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    HuggingFaceFW/fineweb
    Features
    16,384
    Data Type
    torch.float32
    Hook Point
    blocks.0.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    HuggingFaceFW/fineweb
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    313
    +0.14
    0.4%
    1492
    +0.09
    0.3%
    122
    +0.09
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1363
    +0.14
    0.02
    57
    +0.09
    0.02
    1387
    +0.09
    0.02
    Negative Logits
    <bos>
    -1.16
     kapp
    -0.59
     rik
    -0.58
     meren
    -0.56
     pü
    -0.55
     roh
    -0.55
    ///////////////
    -0.55
     talle
    -0.52
     mitte
    -0.52
     kelle
    -0.51
    POSITIVE LOGITS
     Jean
    1.54
    Jean
    1.41
    JEAN
    1.18
     JEAN
    1.15
     jean
    0.90
    jean
    0.84
     soulign
    0.82
     indestru
    0.81
     gentlemen
    0.80
     shenan
    0.80
    Activations Density 0.240%

    No Known Activations