© 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. 3513
    Prev
    Next
    INDEX
    Explanations

    mentions of sports and news-related terms

    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
    1150
    +0.15
    0.4%
    674
    +0.13
    0.4%
    906
    +0.08
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1900
    +0.15
    0.02
    1471
    +0.13
    0.03
    906
    +0.08
    0.00
    Negative Logits
    Molto
    -0.79
    Anche
    -0.79
    Ogni
    -0.79
    Abbiamo
    -0.76
    Kto
    -0.75
    Oltre
    -0.75
    Inoltre
    -0.74
    Siamo
    -0.73
    Buongiorno
    -0.71
    Pasos
    -0.71
    POSITIVE LOGITS
     impra
    1.02
    <bos>
    1.01
     intermitt
    0.97
     suscep
    0.93
     unve
    0.88
     depic
    0.88
     uniqu
    0.82
     fortn
    0.81
     resear
    0.81
     strick
    0.80
    Activations Density 0.203%

    No Known Activations