© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Initial Gemma-2B-IT SAEs
    5. Gemma-2B-IT
    7. Residual Stream
    9. 12-RES-JB
    11. 3433
    Prev
    Next
    INDEX
    Explanations

    mentions of private entities or businesses

    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
    577
    +0.13
    0.5%
    920
    +0.13
    0.5%
    757
    +0.12
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1994
    +0.13
    0.03
    920
    +0.13
    0.03
    757
    +0.12
    0.04
    Negative Logits
     affor
    -0.80
     guarante
    -0.80
     unden
    -0.78
     fortn
    -0.77
     leaft
    -0.76
     vry
    -0.75
     parch
    -0.73
     perfet
    -0.73
     ikea
    -0.72
     jacques
    -0.72
    POSITIVE LOGITS
     private
    1.32
     Private
    1.22
    Private
    1.21
    private
    1.14
     PRIVATE
    1.05
    PRIVATE
    1.01
     privately
    0.91
     privada
    0.81
    priv
    0.77
     privati
    0.75
    Activations Density 0.071%

    No Known Activations