© 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. 13738
    Prev
    Next
    INDEX
    Explanations

    sporting events and competitions

    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
    764
    +0.14
    0.4%
    1842
    +0.12
    0.4%
    906
    +0.10
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    648
    +0.14
    0.05
    1551
    +0.12
    0.05
    764
    +0.10
    0.05
    Negative Logits
     bromine
    -0.71
     tetrach
    -0.69
     nutella
    -0.68
     apricots
    -0.68
     linseed
    -0.68
     polenta
    -0.67
     purée
    -0.67
    salty
    -0.66
     surfactants
    -0.66
     pectin
    -0.65
    POSITIVE LOGITS
     kosme
    1.34
     praktik
    1.30
     minimalis
    1.30
     Strukt
    1.20
     konserv
    1.17
     kompati
    1.16
     konkre
    1.16
     kooper
    1.15
     alkoh
    1.15
     kön
    1.15
    Activations Density 0.344%

    No Known Activations