© 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. 3356
    Prev
    Next
    INDEX
    Explanations

    technical terms related to computer processors and functionalities

    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
    888
    +0.08
    0.2%
    876
    +0.08
    0.2%
    1789
    +0.07
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    870
    +0.08
    0.04
    1789
    +0.08
    0.03
    602
    +0.07
    0.03
    Negative Logits
    LookAnd
    -0.78
    StructEnd
    -0.61
    fromnode
    -0.57
    InstrumentedTest
    -0.56
     bahay
    -0.56
    IndentedString
    -0.54
    IVEREF
    -0.53
     SUDOC
    -0.52
    Palmar
    -0.51
    Schriften
    -0.51
    POSITIVE LOGITS
     simultaneously
    1.10
     simultaneous
    0.99
    simult
    0.96
     Simultaneously
    0.94
     simult
    0.89
     concurrently
    0.89
     Simultaneous
    0.84
    Simult
    0.83
     consecutively
    0.73
     gleichzeitig
    0.71
    Activations Density 0.372%

    No Known Activations