© 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. 6-RES-JB
    6. 6971
    Prev
    Next
    INDEX
    Explanations

    information related to sports games, teams, records, and player performances

    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
    +0.27
    1.0%
    1499
    +0.08
    0.3%
    781
    +0.08
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1419
    +0.27
    0.07
    1905
    +0.08
    0.07
    244
    +0.08
    0.07
    Negative Logits
    <bos>
    -2.53
    mergeFrom
    -0.85
    ItemBackground
    -0.85
    HideFlags
    -0.80
     CWE
    -0.80
     OnTrigger
    -0.79
    Autoritní
    -0.77
     mergeFrom
    -0.76
     fieldNum
    -0.75
    styleType
    -0.74
    POSITIVE LOGITS
     accla
    1.80
     reluct
    1.76
     impra
    1.74
     maneu
    1.73
     affor
    1.67
     shenan
    1.66
     snoopy
    1.59
     apprehen
    1.58
     wherea
    1.58
     strick
    1.57
    Activations Density 0.313%

    No Known Activations