© 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. 14471
    Prev
    Next
    INDEX
    Explanations

    inventors and their famous machines

    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
    872
    +0.14
    0.4%
    1385
    +0.11
    0.3%
    2015
    +0.10
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1705
    +0.14
    0.06
    724
    +0.11
    0.04
    1438
    +0.10
    0.03
    Negative Logits
     akut
    -1.47
     makro
    -1.43
     panik
    -1.41
     alkoh
    -1.39
     kram
    -1.39
     kosme
    -1.33
     bera
    -1.30
     keramik
    -1.26
     hek
    -1.25
     plak
    -1.24
    POSITIVE LOGITS
     embodi
    1.01
     swarovski
    0.95
     ecru
    0.94
     lamella
    0.88
     conftest
    0.88
     flocc
    0.87
     hairc
    0.84
     linseed
    0.83
     regardant
    0.83
     carbonic
    0.82
    Activations Density 0.707%

    No Known Activations