© 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. 3316
    Prev
    Next
    INDEX
    Explanations

    named locations

    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
    50
    +0.14
    0.5%
    752
    +0.14
    0.4%
    1967
    +0.14
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    752
    +0.14
    0.03
    1334
    +0.14
    0.03
    16
    +0.14
    0.04
    Negative Logits
     wspania
    -0.78
     nadzie
    -0.74
     serce
    -0.73
     špat
    -0.70
     będę
    -0.70
     poważ
    -0.68
     niestety
    -0.68
     nikt
    -0.68
     potrze
    -0.67
     uwag
    -0.66
    POSITIVE LOGITS
     Cfr
    1.41
     Perci
    1.27
     Juf
    1.23
     Egli
    1.18
     Chá
    1.16
     alkoh
    1.14
     Strukt
    1.13
     Jof
    1.12
     kön
    1.12
     Abbé
    1.11
    Activations Density 0.152%

    No Known Activations