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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Initial Gemma-2B SAEs
    5. Gemma-2B
    7. Residual Stream
    9. 6-RES-JB
    11. 4139
    Prev
    Next
    INDEX
    Explanations

    positive emotions and reactions

    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
    +0.17
    0.7%
    878
    +0.09
    0.3%
    1445
    +0.09
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    446
    +0.17
    0.06
    1260
    +0.09
    0.05
    1839
    +0.09
    0.07
    Negative Logits
    <bos>
    -1.50
     itself
    -0.71
    <?
    -0.61
    Embeddable
    -0.60
    Pageable
    -0.58
    var
    -0.56
    ManyToMany
    -0.56
    Verdana
    -0.56
    OneToMany
    -0.56
     /**
    -0.55
    POSITIVE LOGITS
     maneu
    1.28
     shenan
    1.27
     accla
    1.24
     reluct
    1.24
     fortn
    1.20
     erad
    1.11
     increa
    1.11
     tramont
    1.07
     compen
    1.07
     strick
    1.06
    Activations Density 1.027%

    No Known Activations