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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Initial Gemma-2B SAEs
    5. Gemma-2B
    7. Residual Stream
    9. 6-RES-JB
    11. 387
    Prev
    Next
    INDEX
    Explanations

    phrases related to capabilities or abilities

    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
    +0.15
    0.8%
    1806
    +0.11
    0.6%
    1047
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1256
    +0.15
    0.04
    1806
    +0.11
    0.04
    1047
    +0.11
    0.04
    Negative Logits
    <bos>
    -3.26
    /***
    -0.84
    /**
    -0.83
     intersper
    -0.80
    ⓧ
    -0.79
    
    -0.79
    <?
    -0.76
     harmonize
    -0.67
     endow
    -0.64
     banish
    -0.62
    POSITIVE LOGITS
     ananas
    1.00
     thuy
    0.99
     kafe
    0.98
     saar
    0.98
     cannes
    0.97
     kasa
    0.95
     seksi
    0.95
     bandung
    0.93
     maroc
    0.93
     jawa
    0.92
    Activations Density 0.105%

    No Known Activations