© 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. 2789
    Prev
    Next
    INDEX
    Explanations

    mentions of devices such as Kindle Fire and Kindle

    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
    +0.14
    0.5%
    1872
    +0.14
    0.5%
    1351
    +0.12
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    783
    +0.14
    0.03
    1872
    +0.14
    0.03
    1351
    +0.12
    0.02
    Negative Logits
    <bos>
    -2.20
    ⓧ
    -0.97
    migrationBuilder
    -0.80
    <?
    -0.63
    rungsseite
    -0.63
    amaño
    -0.63
    дивиду
    -0.61
     referenties
    -0.60
    Ос
    -0.60
    Життєпис
    -0.59
    POSITIVE LOGITS
     Czechos
    1.04
     bandung
    1.03
     Kindle
    1.02
    Kindle
    1.01
     thuy
    1.01
     saar
    1.00
     territo
    0.99
     Pekan
    0.98
     panama
    0.97
     amsterdam
    0.96
    Activations Density 0.130%

    No Known Activations