© 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. 6-RES-JB
    11. 3594
    Prev
    Next
    INDEX
    Explanations

    phrases related to aid and assistance

    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
    +0.15
    0.8%
    1896
    +0.13
    0.8%
    1892
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1515
    +0.15
    0.03
    1892
    +0.13
    0.03
    1896
    +0.12
    0.02
    Negative Logits
    <bos>
    -2.67
    -0.72
        
    -0.70
    bl
    -0.70
    HasAnnotation
    -0.69
    حياته
    -0.68
    -0.67
    มาะ
    -0.65
    cb
    -0.64
            
    -0.64
    POSITIVE LOGITS
     affor
    1.69
     unwarran
    1.69
     impra
    1.59
     increa
    1.58
     unlaw
    1.58
     stockholm
    1.57
     maneu
    1.57
     milf
    1.55
     disagre
    1.54
     toledo
    1.53
    Activations Density 0.172%

    No Known Activations