© 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. 693
    Prev
    Next
    INDEX
    Explanations

    technical specifications and product features related to HDMI and home theater devices

    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
    678
    +0.09
    0.3%
    690
    +0.08
    0.3%
    823
    +0.08
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    823
    +0.09
    0.06
    690
    +0.08
    0.05
    678
    +0.08
    0.04
    Negative Logits
    ⓧ
    -0.78
    
    
    -0.66
     lie
    -0.63
     demanded
    -0.63
     intervened
    -0.63
     fill
    -0.62
     encourage
    -0.62
     manage
    -0.61
     denounce
    -0.61
     provide
    -0.61
    POSITIVE LOGITS
     autunno
    1.48
     paradiso
    1.42
     hdmi
    1.38
     embodi
    1.38
     bacio
    1.35
     affez
    1.35
     geforce
    1.33
     maroc
    1.32
     milano
    1.31
     papà
    1.30
    Activations Density 0.229%

    No Known Activations