© 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. 13823
    Prev
    Next
    INDEX
    Explanations

    mentions of specific usernames in social media related to requests or provocations

    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
    1757
    +0.16
    0.6%
    25
    +0.14
    0.6%
    538
    +0.14
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    538
    +0.16
    0.05
    981
    +0.14
    0.05
    390
    +0.14
    0.04
    Negative Logits
     tramonto
    -0.56
    ethene
    -0.55
     medesimo
    -0.53
     paesaggio
    -0.52
     допомогти
    -0.52
     cammino
    -0.51
    ethane
    -0.50
     ritratto
    -0.50
     cristianismo
    -0.47
     tentativo
    -0.47
    POSITIVE LOGITS
     lü
    0.98
     hek
    0.96
     minimalis
    0.94
     klo
    0.93
     konkre
    0.92
     makro
    0.91
     kompati
    0.90
     alkoh
    0.89
     panik
    0.88
     stoff
    0.88
    Activations Density 0.256%

    No Known Activations