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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 5907
    Prev
    Next
    INDEX
    Explanations

    band names

    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
    156
    +0.17
    0.8%
    1624
    +0.13
    0.7%
    545
    +0.13
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    156
    +0.17
    0.03
    1624
    +0.13
    0.03
    1056
    +0.13
    0.03
    Negative Logits
    <bos>
    -2.12
    public
    -0.73
    ve
    -0.66
    ChildScrollView
    -0.65
    HasIndex
    -0.64
    ·
    -0.62
    Tikang
    -0.62
    IsUnicode
    -0.61
    ...
    -0.61
    module
    -0.61
    POSITIVE LOGITS
     olx
    1.45
     stockholm
    1.45
     sergio
    1.44
     ricardo
    1.41
     jorge
    1.40
     seoul
    1.39
     roberto
    1.38
     wien
    1.38
     lidl
    1.35
     mef
    1.34
    Activations Density 0.273%

    No Known Activations