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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Initial Gemma-2B-IT SAEs
    5. Gemma-2B-IT
    7. Residual Stream
    9. 12-RES-JB
    11. 12431
    Prev
    Next
    INDEX
    Explanations

    text related to medical conditions and diseases

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    jbloom/Gemma-2b-IT-Residual-Stream-SAEs/gemma_2b_it_blocks.12.hook_resid_post_16384
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    HuggingFaceFW/fineweb
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    standard
    Context Size
    1,024
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    674
    +0.36
    1.5%
    856
    +0.16
    0.7%
    998
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1823
    +0.36
    0.03
    845
    +0.16
    0.03
    1960
    +0.09
    0.01
    Negative Logits
     Telex
    -0.52
     Petitioners
    -0.50
     Heeren
    -0.50
     Sted
    -0.49
     Gorb
    -0.47
     Fulda
    -0.47
     Durand
    -0.46
     Eder
    -0.46
    TypedValue
    -0.45
     Comstock
    -0.45
    POSITIVE LOGITS
    <bos>
    1.35
    ⓧ
    0.80
     soggior
    0.79
     disambiguazione
    0.78
    /***
    0.73
     Roskov
    0.73
    principalTable
    0.72
    /**
    0.72
    💼
    0.72
    /*
    0.71
    Activations Density 1.436%

    No Known Activations