© 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. 14211
    Prev
    Next
    INDEX
    Explanations

    phrases related to policies or official statements

    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
    1870
    +0.14
    0.4%
    1150
    +0.12
    0.3%
    332
    +0.10
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    332
    +0.14
    0.06
    1287
    +0.12
    0.04
    1719
    +0.10
    0.05
    Negative Logits
     meis
    -1.05
     hej
    -1.05
     ananas
    -1.03
     kram
    -1.03
    intenance
    -1.02
     lancia
    -1.01
     logis
    -1.01
     lele
    -1.01
     ordina
    -1.00
     apparti
    -0.97
    POSITIVE LOGITS
    jątk
    0.65
     about
    0.58
    spesies
    0.56
     regarding
    0.54
    about
    0.52
     on
    0.51
     concerning
    0.51
     proposal
    0.49
    Kiedy
    0.49
    ings
    0.49
    Activations Density 0.373%

    No Known Activations