Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Initial Gemma-2B SAEs
    3. Gemma-2B
    4. Residual Stream
    5. 6-RES-JB
    6. 6407
    Prev
    Next
    INDEX
    Explanations

    details about historical events or fictional plots, potentially related to treasure hunts

    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
    +0.18
    0.7%
    184
    +0.13
    0.5%
    1978
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    184
    +0.18
    -0.03
    1978
    +0.13
    0.12
    964
    +0.10
    0.09
    Negative Logits
    <bos>
    -3.23
    Vidite
    -0.84
    Билгалдахарш
    -0.83
    /***
    
    -0.80
     springfox
    -0.79
    Autoritní
    -0.79
    ⓧ
    -0.78
     autorytatywna
    -0.77
     Мексичка
    -0.76
    ьаж
    -0.72
    POSITIVE LOGITS
     affor
    1.20
     alip
    1.18
     maksi
    1.16
     eki
    1.14
     seksi
    1.14
     kafe
    1.13
     silikon
    1.12
     kask
    1.10
     unlaw
    1.10
     maneu
    1.08
    Activations Density 2.370%

    No Known Activations