© 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. 7773
    Prev
    Next
    INDEX
    Explanations

    descriptions of a city with its different parts and features

    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
    1385
    +0.23
    0.7%
    198
    +0.15
    0.5%
    906
    +0.13
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    939
    +0.23
    0.07
    198
    +0.15
    0.05
    1385
    +0.13
    0.05
    Negative Logits
     incess
    -0.93
     stoff
    -0.87
     kosme
    -0.86
     pessi
    -0.86
     klap
    -0.85
     praktik
    -0.84
     minimalis
    -0.83
     imposs
    -0.81
     klok
    -0.81
     alkoh
    -0.77
    POSITIVE LOGITS
     buildings
    0.62
     houses
    0.59
     jette
    0.58
     trees
    0.52
     residential
    0.52
     createdBy
    0.52
     dwellings
    0.52
     residences
    0.51
     shops
    0.50
     vegetation
    0.48
    Activations Density 0.476%

    No Known Activations