© 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. 6448
    Prev
    Next
    INDEX
    Explanations

    product details, including specifications and instructions, possibly related to electronic devices or home products

    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
    +0.31
    1.3%
    1150
    +0.10
    0.4%
    453
    +0.08
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    453
    +0.31
    0.09
    1150
    +0.10
    0.03
    1403
    +0.08
    0.04
    Negative Logits
    <bos>
    -2.90
    ⓧ
    -0.89
    <?
    -0.89
    /*
    -0.84
    ValueGenerated
    -0.76
    HasOne
    -0.75
    public
    -0.74
    addComponent
    -0.74
    /**
    -0.72
    OneToMany
    -0.71
    POSITIVE LOGITS
     increa
    2.17
     maneu
    2.15
     accla
    2.10
     affor
    2.09
     volunte
    2.07
     inev
    2.03
     guarante
    2.00
     disagre
    2.00
     depic
    1.96
     resear
    1.94
    Activations Density 1.212%

    No Known Activations