© 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. 13760
    Prev
    Next
    INDEX
    Explanations

    phrases related to basketball defense strategies

    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
    604
    +0.10
    0.3%
    1531
    +0.10
    0.3%
    1842
    +0.09
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    39
    +0.10
    0.02
    818
    +0.10
    0.04
    1531
    +0.09
    0.03
    Negative Logits
     depic
    -1.27
     encomp
    -1.24
     increa
    -1.09
     purcha
    -1.08
     volunte
    -1.07
     disagre
    -1.05
     inev
    -1.04
     unspeak
    -1.02
     Intere
    -1.02
     berea
    -1.01
    POSITIVE LOGITS
    ENODEV
    0.63
     ostavi
    0.62
     himo
    0.58
    RegistryLite
    0.58
     IndexError
    0.52
     unable
    0.52
     weakness
    0.51
     onCancelled
    0.51
     fail
    0.51
    weakSelf
    0.50
    Activations Density 0.336%

    No Known Activations