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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Initial Gemma-2B SAEs
    5. Gemma-2B
    7. Residual Stream
    9. 0-RES-JB
    11. 1084
    Prev
    Next
    INDEX
    Explanations

    locations or objects where something can be hung

    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
    50
    +0.08
    0.3%
    783
    +0.07
    0.3%
    795
    +0.06
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    957
    +0.08
    0.04
    403
    +0.07
    0.03
    154
    +0.06
    0.03
    Negative Logits
    <bos>
    -1.28
    public
    -0.71
    qiu
    -0.66
    else
    -0.66
    qiao
    -0.64
    ⓧ
    -0.64
    /**
    -0.63
    -0.63
    ,
    -0.63
    	
    -0.63
    POSITIVE LOGITS
     hang
    2.49
     Hang
    2.28
     HANG
    2.24
    Hang
    2.19
     hangs
    2.15
     hanging
    2.03
     Hanging
    2.00
    Hanging
    2.00
    hanging
    1.97
     hung
    1.95
    Activations Density 0.123%
    No Known Activations