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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Initial Gemma-2B SAEs
    3. Gemma-2B
    4. Residual Stream
    5. 6-RES-JB
    6. 8876
    Prev
    Next
    INDEX
    Explanations

    mentions of specific types of batteries

    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
    313
    +0.19
    1.0%
    1624
    +0.16
    0.9%
    228
    +0.16
    0.9%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1097
    +0.19
    0.05
    228
    +0.16
    0.04
    1622
    +0.16
    0.03
    Negative Logits
    <bos>
    -1.18
    parsedMessage
    -0.63
    matchCondition
    -0.54
    sizeCache
    -0.54
    TintMode
    -0.53
    ItemBackground
    -0.53
    djangoproject
    -0.52
    isContained
    -0.51
     Italijani
    -0.51
    <?
    -0.51
    POSITIVE LOGITS
     Ni
    1.23
    Ni
    1.18
     Nickel
    0.93
     ni
    0.92
     Niall
    0.91
     nicolas
    0.91
     nickel
    0.89
     ricardo
    0.88
     wattpad
    0.88
     venice
    0.88
    Activations Density 0.459%

    No Known Activations