© 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. 13044
    Prev
    Next
    INDEX
    Explanations

    phrases related to group comparisons, mutual actions, or comparisons between two entities

    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
    946
    +0.10
    0.3%
    198
    +0.09
    0.3%
    184
    +0.08
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1792
    +0.10
    0.04
    1041
    +0.09
    0.03
    198
    +0.08
    0.03
    Negative Logits
     anse
    -0.66
     utop
    -0.63
     meras
    -0.61
     alfabe
    -0.60
     asma
    -0.59
     sement
    -0.59
     benzin
    -0.58
     poros
    -0.58
     elek
    -0.58
     dita
    -0.58
    POSITIVE LOGITS
     reluct
    1.22
     tolerably
    1.16
     apprehen
    1.12
     intersper
    1.11
     shenan
    1.11
     disagre
    1.07
     encomp
    1.07
     unspeak
    1.07
     fortn
    1.05
     reconno
    1.05
    Activations Density 0.161%

    No Known Activations