© 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. 4813
    Prev
    Next
    INDEX
    Explanations

    phrases related to overcoming challenges or difficulties

    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
    2004
    +0.15
    0.7%
    805
    +0.11
    0.5%
    1065
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1622
    +0.15
    0.03
    2004
    +0.11
    0.03
    1142
    +0.11
    0.03
    Negative Logits
    <bos>
    -1.68
    Uso
    -0.60
     band
    -0.57
     cur
    -0.56
    TextEditing
    -0.55
     like
    -0.55
    꼬
    -0.55
    Banda
    -0.55
     san
    -0.54
    Adic
    -0.54
    POSITIVE LOGITS
     jaya
    1.40
     bandung
    1.36
     yong
    1.32
     haup
    1.25
     lele
    1.25
     napoli
    1.24
     kark
    1.22
     kyo
    1.21
     meis
    1.20
     stockholm
    1.20
    Activations Density 0.442%

    No Known Activations