© 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. 0-RES-JB
    11. 327
    Prev
    Next
    INDEX
    Explanations

    words related to sales or promotions

    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
    554
    +0.09
    0.3%
    1590
    +0.08
    0.3%
    1407
    +0.08
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1363
    +0.09
    0.02
    1372
    +0.08
    0.02
    1590
    +0.08
    0.02
    Negative Logits
    ATEGY
    -0.62
    <bos>
    -0.56
    ANDUM
    -0.56
    ocarcinoma
    -0.56
    േ
    -0.54
    AsUp
    -0.54
    ContentAlignment
    -0.54
    NOSIS
    -0.54
    CodeAttribute
    -0.53
    ുറ
    -0.53
    POSITIVE LOGITS
     ped
    2.81
     Ped
    2.81
    Ped
    2.60
    ped
    2.39
     PED
    2.23
     Pedal
    1.85
    pedal
    1.77
    PED
    1.76
     pedal
    1.75
     pedals
    1.67
    Activations Density 0.202%

    No Known Activations