© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Joseph Bloom · Initial Gemma-2B SAEs
    3. Gemma-2B
    4. Residual Stream
    5. 10-RES-JB
    6. 3055
    Prev
    Next
    INDEX
    Explanations

    numerical references and metrics, particularly relating to performance and technical specifications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    jbloom/Gemma-2b-Residual-Stream-SAEs/gemma_2b_blocks.10.hook_resid_post_16384
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    chanind/openwebtext-gemma
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    standard
    Context Size
    1,024
    Dataset
    ctigges/openwebtext-gemma-1024-cl
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    50
    +0.19
    1.0%
    1505
    +0.10
    0.5%
    1233
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    2036
    +0.19
    0.05
    1978
    +0.10
    0.06
    1505
    +0.10
    0.06
    Negative Logits
    <bos>
    -2.47
     intersper
    -1.36
     quitted
    -1.01
     encomp
    -0.98
    ⓧ
    -0.95
     darted
    -0.93
     shuddered
    -0.92
     endow
    -0.91
     disbur
    -0.90
     vainly
    -0.89
    POSITIVE LOGITS
     Antropo
    0.82
     Trasp
    0.75
     ados
    0.73
     Gestão
    0.71
     parati
    0.71
     jawa
    0.71
     kafe
    0.71
     sirop
    0.70
     Jerusal
    0.69
     Água
    0.69
    Activations Density 0.163%

    No Known Activations