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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Joseph Bloom · Initial Gemma-2B SAEs
    3. Gemma-2B
    4. Residual Stream
    5. 0-RES-JB
    6. 1001
    Prev
    Next
    INDEX
    Explanations

    scientific and technical information such as citations, research studies, and academic references

    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.0.hook_resid_post_16384_anthropic
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    HuggingFaceFW/fineweb
    Features
    16,384
    Data Type
    torch.float32
    Hook Point
    blocks.0.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    HuggingFaceFW/fineweb
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    555
    +0.07
    0.3%
    50
    +0.07
    0.3%
    1052
    +0.07
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    424
    +0.07
    0.03
    1233
    +0.07
    0.03
    1593
    +0.07
    0.03
    Negative Logits
    <bos>
    -0.98
    public
    -0.68
     kwamen
    -0.66
    </tbody>
    -0.65
    enumerate
    -0.65
    itemize
    -0.64
    protected
    -0.64
                    
    -0.63
    SPECTION
    -0.63
                
    -0.62
    POSITIVE LOGITS
     Vol
    2.56
    Vol
    2.39
     vol
    2.34
     volunte
    2.17
     VOL
    2.09
    vol
    2.07
     affor
    1.89
    VOL
    1.80
     volu
    1.75
     quoique
    1.74
    Activations Density 0.104%

    No Known Activations