Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Initial Gemma-2B-IT SAEs
    3. Gemma-2B-IT
    4. Residual Stream
    5. 12-RES-JB
    6. 2699
    Prev
    Next
    INDEX
    Explanations

    numeric values or quantities

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    jbloom/Gemma-2b-IT-Residual-Stream-SAEs/gemma_2b_it_blocks.12.hook_resid_post_16384
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    HuggingFaceFW/fineweb
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    standard
    Context Size
    1,024
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    1253
    +0.10
    0.3%
    1793
    +0.09
    0.3%
    1839
    +0.09
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1856
    +0.10
    0.02
    1499
    +0.09
    0.02
    1793
    +0.09
    0.02
    Negative Logits
     newArr
    -0.71
     bapt
    -0.63
     confé
    -0.60
     maît
    -0.58
     Presbyter
    -0.56
     citoy
    -0.56
     Krzysz
    -0.56
     soeur
    -0.55
     jsonData
    -0.53
     africain
    -0.52
    POSITIVE LOGITS
     median
    1.05
    Median
    0.87
     Median
    0.85
    median
    0.82
     mediana
    0.76
     mean
    0.63
     average
    0.58
     household
    0.57
    <bos>
    0.52
     medi
    0.51
    Activations Density 0.086%

    No Known Activations