© 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. 7762
    Prev
    Next
    INDEX
    Explanations

    combinations of numbers and state names, potentially related to races or events

    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
    1978
    +0.12
    0.3%
    1343
    +0.09
    0.2%
    490
    +0.09
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1343
    +0.12
    0.05
    480
    +0.09
    0.04
    1978
    +0.09
    0.05
    Negative Logits
     незавершена
    -0.66
     referrerpolicy
    -0.60
    TargetApi
    -0.60
    сылкі
    -0.55
    Nachdem
    -0.55
    Datuak
    -0.54
    Dazu
    -0.54
     ExecuteAsync
    -0.53
    Personendaten
    -0.53
    Vielen
    -0.53
    POSITIVE LOGITS
     emphat
    1.21
     fatis
    1.18
     paff
    1.14
     fuf
    1.08
     §.
    1.08
     ftre
    1.05
     dsg
    1.05
     fta
    1.05
     perfet
    1.03
     ?...
    1.01
    Activations Density 0.214%

    No Known Activations