© 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
    2. Joseph Bloom · Initial Gemma-2B-IT SAEs
    3. Gemma-2B-IT
    4. Residual Stream
    5. 12-RES-JB
    6. 13078
    Prev
    Next
    INDEX
    Explanations

    information related to sports matches and player performance

    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
    599
    +0.12
    0.4%
    658
    +0.11
    0.3%
    1842
    +0.10
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    658
    +0.12
    0.06
    599
    +0.11
    0.06
    392
    +0.10
    0.03
    Negative Logits
     swarovski
    -1.09
     anhyd
    -1.07
     oleo
    -1.07
     embodi
    -1.07
     [''
    -1.06
     zirc
    -1.02
     leonardo
    -0.99
     pollut
    -0.98
     alberto
    -0.98
     Whence
    -0.96
    POSITIVE LOGITS
    <bos>
    0.78
     disiplin
    0.57
     ourselves
    0.57
     team
    0.56
     tonight
    0.53
     defense
    0.51
     win
    0.50
     offence
    0.50
     winning
    0.50
     defence
    0.50
    Activations Density 0.306%

    No Known Activations