© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Initial Gemma-2B SAEs
    5. Gemma-2B
    7. Residual Stream
    9. 6-RES-JB
    11. 5786
    Prev
    Next
    INDEX
    Explanations

    medical terms related to the spread of tumors

    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
    1.0%
    341
    +0.13
    0.8%
    1581
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    341
    +0.17
    0.03
    1581
    +0.13
    0.03
    370
    +0.12
    0.03
    Negative Logits
    <bos>
    -3.42
    HasColumnType
    -0.82
    protected
    -0.82
    IActionResult
    -0.82
    XtraBars
    -0.81
    public
    -0.79
    int
    -0.79
    HasIndex
    -0.79
    /**
    -0.78
     am
    -0.77
    POSITIVE LOGITS
     increa
    2.49
     ftu
    2.46
     affor
    2.42
     maneu
    2.41
     fta
    2.38
     milf
    2.37
     eiffel
    2.32
     madonna
    2.30
     impra
    2.29
     indestru
    2.29
    Activations Density 0.130%

    No Known Activations